Speech
-
CA-SSLR: Condition-Aware Self-Supervised Learning Representation for Generalized Speech Processing
2024-12-05 18:51:10Yen-Ju Lu, Jing Liu, Thomas Thebaud, Laureano Moro-Velazquez, Ariya Rastrow, Najim Dehak, Jesus VillalbaAbstract
We introduce Condition-Aware Self-Supervised Learning Representation (CA-SSLR), a generalist conditioning model broadly applicable to various speech-processing tasks. Compared to standard fine-tuning methods that optimize for downstream models, CA-SSLR integrates language and speaker embeddings from earlier layers, making the SSL model aware of the current language and speaker context. This approach reduces the reliance on input audio features while preserving the integrity of the base SSLR. CA-SSLR improves the model's capabilities and demonstrates its generality on unseen tasks with minimal task-specific tuning. Our method employs linear modulation to dynamically adjust internal representations, enabling fine-grained adaptability without significantly altering the original model behavior. Experiments show that CA-SSLR reduces the number of trainable parameters, mitigates overfitting, and excels in under-resourced and unseen tasks. Specifically, CA-SSLR achieves a 10% relative reduction in LID errors, a 37% improvement in ASR CER on the ML-SUPERB benchmark, and a 27% decrease in SV EER on VoxCeleb-1, demonstrating its effectiveness.
Abstract (translated)
URL
https://arxiv.org/abs/2412.04425
PDF
-
Representation Purification for End-to-End Speech Translation
2024-12-05 15:50:44Chengwei Zhang, Yue Zhou, Rui Zhao, Yidong Chen, Xiaodong ShiAbstract
Speech-to-text translation (ST) is a cross-modal task that involves converting spoken language into text in a different language. Previous research primarily focused on enhancing speech translation by facilitating knowledge transfer from machine translation, exploring various methods to bridge the gap between speech and text modalities. Despite substantial progress made, factors in speech that are not relevant to translation content, such as timbre and rhythm, often limit the efficiency of knowledge transfer. In this paper, we conceptualize speech representation as a combination of content-agnostic and content-relevant factors. We examine the impact of content-agnostic factors on translation performance through preliminary experiments and observe a significant performance deterioration when content-agnostic perturbations are introduced to speech signals. To address this issue, we propose a \textbf{S}peech \textbf{R}epresentation \textbf{P}urification with \textbf{S}upervision \textbf{E}nhancement (SRPSE) framework, which excludes the content-agnostic components within speech representations to mitigate their negative impact on ST. Experiments on MuST-C and CoVoST-2 datasets demonstrate that SRPSE significantly improves translation performance across all translation directions in three settings and achieves preeminent performance under a \textit{transcript-free} setting.
Abstract (translated)
URL
https://arxiv.org/abs/2412.04266
PDF
-
Speech Recognition-based Feature Extraction for Enhanced Automatic Severity Classification in Dysarthric Speech
2024-12-05 00:12:53Yerin Choi, Jeehyun Lee, Myoung-Wan KooAbstract
Due to the subjective nature of current clinical evaluation, the need for automatic severity evaluation in dysarthric speech has emerged. DNN models outperform ML models but lack user-friendly explainability. ML models offer explainable results at a feature level, but their performance is comparatively lower. Current ML models extract various features from raw waveforms to predict severity. However, existing methods do not encompass all dysarthric features used in clinical evaluation. To address this gap, we propose a feature extraction method that minimizes information loss. We introduce an ASR transcription as a novel feature extraction source. We finetune the ASR model for dysarthric speech, then use this model to transcribe dysarthric speech and extract word segment boundary information. It enables capturing finer pronunciation and broader prosodic features. These features demonstrated an improved severity prediction performance to existing features: balanced accuracy of 83.72%.
Abstract (translated)
URL
https://arxiv.org/abs/2412.03784
PDF
-
DiffStyleTTS: Diffusion-based Hierarchical Prosody Modeling for Text-to-Speech with Diverse and Controllable Styles
2024-12-04 15:17:25Jiaxuan Liu, Zhaoci Liu, Yajun Hu, Yingying Gao, Shilei Zhang, Zhenhua LingAbstract
Human speech exhibits rich and flexible prosodic variations. To address the one-to-many mapping problem from text to prosody in a reasonable and flexible manner, we propose DiffStyleTTS, a multi-speaker acoustic model based on a conditional diffusion module and an improved classifier-free guidance, which hierarchically models speech prosodic features, and controls different prosodic styles to guide prosody prediction. Experiments show that our method outperforms all baselines in naturalness and achieves superior synthesis speed compared to three diffusion-based baselines. Additionally, by adjusting the guiding scale, DiffStyleTTS effectively controls the guidance intensity of the synthetic prosody.
Abstract (translated)
URL
https://arxiv.org/abs/2412.03388
PDF
-
ASR-EC Benchmark: Evaluating Large Language Models on Chinese ASR Error Correction
2024-12-04 06:52:10Victor Junqiu Wei, Weicheng Wang, Di Jiang, Yuanfeng Song, Lu WangAbstract
Automatic speech Recognition (ASR) is a fundamental and important task in the field of speech and natural language processing. It is an inherent building block in many applications such as voice assistant, speech translation, etc. Despite the advancement of ASR technologies in recent years, it is still inevitable for modern ASR systems to have a substantial number of erroneous recognition due to environmental noise, ambiguity, etc. Therefore, the error correction in ASR is crucial. Motivated by this, this paper studies ASR error correction in the Chinese language, which is one of the most popular languages and enjoys a large number of users in the world. We first create a benchmark dataset named \emph{ASR-EC} that contains a wide spectrum of ASR errors generated by industry-grade ASR systems. To the best of our knowledge, it is the first Chinese ASR error correction benchmark. Then, inspired by the recent advances in \emph{large language models (LLMs)}, we investigate how to harness the power of LLMs to correct ASR errors. We apply LLMs to ASR error correction in three paradigms. The first paradigm is prompting, which is further categorized as zero-shot, few-shot, and multi-step. The second paradigm is finetuning, which finetunes LLMs with ASR error correction data. The third paradigm is multi-modal augmentation, which collectively utilizes the audio and ASR transcripts for error correction. Extensive experiments reveal that prompting is not effective for ASR error correction. Finetuning is effective only for a portion of LLMs. Multi-modal augmentation is the most effective method for error correction and achieves state-of-the-art performance.
Abstract (translated)
URL
https://arxiv.org/abs/2412.03075
PDF
-
Analytic Study of Text-Free Speech Synthesis for Raw Audio using a Self-Supervised Learning Model
2024-12-04 06:52:03Joonyong Park, Daisuke Saito, Nobuaki MinematsuAbstract
We examine the text-free speech representations of raw audio obtained from a self-supervised learning (SSL) model by analyzing the synthesized speech using the SSL representations instead of conventional text representations. Since raw audio does not have paired speech representations as transcribed texts do, obtaining speech representations from unpaired speech is crucial for augmenting available datasets for speech synthesis. Specifically, the proposed speech synthesis is conducted using discrete symbol representations from the SSL model in comparison with text representations, and analytical examinations of the synthesized speech have been carried out. The results empirically show that using text representations is advantageous for preserving semantic information, while using discrete symbol representations is superior for preserving acoustic content, including prosodic and intonational information.
Abstract (translated)
URL
https://arxiv.org/abs/2412.03074
PDF
-
GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot
2024-12-03 17:41:24Aohan Zeng, Zhengxiao Du, Mingdao Liu, Kedong Wang, Shengmin Jiang, Lei Zhao, Yuxiao Dong, Jie TangAbstract
We introduce GLM-4-Voice, an intelligent and human-like end-to-end spoken chatbot. It supports both Chinese and English, engages in real-time voice conversations, and varies vocal nuances such as emotion, intonation, speech rate, and dialect according to user instructions. GLM-4-Voice uses an ultra-low bitrate (175bps), single-codebook speech tokenizer with 12.5Hz frame rate derived from an automatic speech recognition (ASR) model by incorporating a vector-quantized bottleneck into the encoder. To efficiently transfer knowledge from text to speech modalities, we synthesize speech-text interleaved data from existing text pre-training corpora using a text-to-token model. We continue pre-training from the pre-trained text language model GLM-4-9B with a combination of unsupervised speech data, interleaved speech-text data, and supervised speech-text data, scaling up to 1 trillion tokens, achieving state-of-the-art performance in both speech language modeling and spoken question answering. We then fine-tune the pre-trained model with high-quality conversational speech data, achieving superior performance compared to existing baselines in both conversational ability and speech quality. The open models can be accessed through this https URL and this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2412.02612
PDF
-
It Takes Two: Real-time Co-Speech Two-person's Interaction Generation via Reactive Auto-regressive Diffusion Model
2024-12-03 12:31:44Mingyi Shi, Dafei Qin, Leo Ho, Zhouyingcheng Liao, Yinghao Huang, Junichi Yamagishi, Taku KomuraAbstract
Conversational scenarios are very common in real-world settings, yet existing co-speech motion synthesis approaches often fall short in these contexts, where one person's audio and gestures will influence the other's responses. Additionally, most existing methods rely on offline sequence-to-sequence frameworks, which are unsuitable for online applications. In this work, we introduce an audio-driven, auto-regressive system designed to synthesize dynamic movements for two characters during a conversation. At the core of our approach is a diffusion-based full-body motion synthesis model, which is conditioned on the past states of both characters, speech audio, and a task-oriented motion trajectory input, allowing for flexible spatial control. To enhance the model's ability to learn diverse interactions, we have enriched existing two-person conversational motion datasets with more dynamic and interactive motions. We evaluate our system through multiple experiments to show it outperforms across a variety of tasks, including single and two-person co-speech motion generation, as well as interactive motion generation. To the best of our knowledge, this is the first system capable of generating interactive full-body motions for two characters from speech in an online manner.
Abstract (translated)
URL
https://arxiv.org/abs/2412.02419
PDF
-
Multi-Granularity Tibetan Textual Adversarial Attack Method Based on Masked Language Model
2024-12-03 10:03:52Xi Cao, Nuo Qun, Quzong Gesang, Yulei Zhu, Trashi NyimaAbstract
In social media, neural network models have been applied to hate speech detection, sentiment analysis, etc., but neural network models are susceptible to adversarial attacks. For instance, in a text classification task, the attacker elaborately introduces perturbations to the original texts that hardly alter the original semantics in order to trick the model into making different predictions. By studying textual adversarial attack methods, the robustness of language models can be evaluated and then improved. Currently, most of the research in this field focuses on English, and there is also a certain amount of research on Chinese. However, there is little research targeting Chinese minority languages. With the rapid development of artificial intelligence technology and the emergence of Chinese minority language models, textual adversarial attacks become a new challenge for the information processing of Chinese minority languages. In response to this situation, we propose a multi-granularity Tibetan textual adversarial attack method based on masked language models called TSTricker. We utilize the masked language models to generate candidate substitution syllables or words, adopt the scoring mechanism to determine the substitution order, and then conduct the attack method on several fine-tuned victim models. The experimental results show that TSTricker reduces the accuracy of the classification models by more than 28.70% and makes the classification models change the predictions of more than 90.60% of the samples, which has an evidently higher attack effect than the baseline method.
Abstract (translated)
URL
https://arxiv.org/abs/2412.02343
PDF
-
Unveiling Interpretability in Self-Supervised Speech Representations for Parkinson's Diagnosis
2024-12-02 22:23:43David Gimeno-G\'omez, Catarina Botelho, Anna Pompili, Alberto Abad, Carlos-D. Mart\'inez-HinarejosAbstract
Recent works in pathological speech analysis have increasingly relied on powerful self-supervised speech representations, leading to promising results. However, the complex, black-box nature of these embeddings and the limited research on their interpretability significantly restrict their adoption for clinical diagnosis. To address this gap, we propose a novel, interpretable framework specifically designed to support Parkinson's Disease (PD) diagnosis. Through the design of simple yet effective cross-attention mechanisms for both embedding- and temporal-level analysis, the proposed framework offers interpretability from two distinct but complementary perspectives. Experimental findings across five well-established speech benchmarks for PD detection demonstrate the framework's capability to identify meaningful speech patterns within self-supervised representations for a wide range of assessment tasks. Fine-grained temporal analyses further underscore its potential to enhance the interpretability of deep-learning pathological speech models, paving the way for the development of more transparent, trustworthy, and clinically applicable computer-assisted diagnosis systems in this domain. Moreover, in terms of classification accuracy, our method achieves results competitive with state-of-the-art approaches, while also demonstrating robustness in cross-lingual scenarios when applied to spontaneous speech production.
Abstract (translated)
URL
https://arxiv.org/abs/2412.02006
PDF
-
I Spy With My Little Eye: A Minimum Cost Multicut Investigation of Dataset Frames
2024-12-02 09:09:47Katharina Prasse, Isaac Bravo, Stefanie Walter, Margret KeuperAbstract
Visual framing analysis is a key method in social sciences for determining common themes and concepts in a given discourse. To reduce manual effort, image clustering can significantly speed up the annotation process. In this work, we phrase the clustering task as a Minimum Cost Multicut Problem [MP]. Solutions to the MP have been shown to provide clusterings that maximize the posterior probability, solely from provided local, pairwise probabilities of two images belonging to the same cluster. We discuss the efficacy of numerous embedding spaces to detect visual frames and show its superiority over other clustering methods. To this end, we employ the climate change dataset \textit{ClimateTV} which contains images commonly used for visual frame analysis. For broad visual frames, DINOv2 is a suitable embedding space, while ConvNeXt V2 returns a larger number of clusters which contain fine-grain differences, i.e. speech and protest. Our insights into embedding space differences in combination with the optimal clustering - by definition - advances automated visual frame detection. Our code can be found at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2412.01296
PDF
-
The Codec Language Model-based Zero-Shot Spontaneous Style TTS System for CoVoC Challenge 2024
2024-12-02 04:17:42Shuoyi Zhou, Yixuan Zhou, Weiqing Li, Jun Chen, Runchuan Ye, Weihao Wu, Zijian Lin, Shun Lei, Zhiyong WuAbstract
This paper describes the zero-shot spontaneous style TTS system for the ISCSLP 2024 Conversational Voice Clone Challenge (CoVoC). We propose a LLaMA-based codec language model with a delay pattern to achieve spontaneous style voice cloning. To improve speech intelligibility, we introduce the Classifier-Free Guidance (CFG) strategy in the language model to strengthen conditional guidance on token prediction. To generate high-quality utterances, we adopt effective data preprocessing operations and fine-tune our model with selected high-quality spontaneous speech data. The official evaluations in the CoVoC constrained track show that our system achieves the best speech naturalness MOS of 3.80 and obtains considerable speech quality and speaker similarity results.
Abstract (translated)
URL
https://arxiv.org/abs/2412.01100
PDF
-
Advancing Speech Language Models by Scaling Supervised Fine-Tuning with Over 60,000 Hours of Synthetic Speech Dialogue Data
2024-12-02 03:31:46Shuaijiang Zhao, Tingwei Guo, Bajian Xiang, Tongtang Wan, Qiang Niu, Wei Zou, Xiangang LiAbstract
The GPT-4o represents a significant milestone in enabling real-time interaction with large language models (LLMs) through speech, its remarkable low latency and high fluency not only capture attention but also stimulate research interest in the field. This real-time speech interaction is particularly valuable in scenarios requiring rapid feedback and immediate responses, dramatically enhancing user experience. However, there is a notable lack of research focused on real-time large speech language models, particularly for Chinese. In this work, we present KE-Omni, a seamless large speech language model built upon Ke-SpeechChat, a large-scale high-quality synthetic speech interaction dataset consisting of 7 million Chinese and English conversations, featuring 42,002 speakers, and totaling over 60,000 hours, This contributes significantly to the advancement of research and development in this field. The model, dataset, code and demo can be accessed at \url{this https URL}.
Abstract (translated)
URL
https://arxiv.org/abs/2412.01078
PDF
-
FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait
2024-12-02 02:50:07Taekyung Ki, Dongchan Min, Gyoungsu ChaeAbstract
With the rapid advancement of diffusion-based generative models, portrait image animation has achieved remarkable results. However, it still faces challenges in temporally consistent video generation and fast sampling due to its iterative sampling nature. This paper presents FLOAT, an audio-driven talking portrait video generation method based on flow matching generative model. We shift the generative modeling from the pixel-based latent space to a learned motion latent space, enabling efficient design of temporally consistent motion. To achieve this, we introduce a transformer-based vector field predictor with a simple yet effective frame-wise conditioning mechanism. Additionally, our method supports speech-driven emotion enhancement, enabling a natural incorporation of expressive motions. Extensive experiments demonstrate that our method outperforms state-of-the-art audio-driven talking portrait methods in terms of visual quality, motion fidelity, and efficiency.
Abstract (translated)
URL
https://arxiv.org/abs/2412.01064
PDF
-
FreeCodec: A disentangled neural speech codec with fewer tokens
2024-12-02 02:29:22Youqiang Zheng, Weiping Tu, Yueteng Kang, Jie Chen, Yike Zhang, Li Xiao, Yuhong Yang, Long MaAbstract
Neural speech codecs have gained great attention for their outstanding reconstruction with discrete token representations. It is a crucial component in generative tasks such as speech coding and large language models (LLM). However, most works based on residual vector quantization perform worse with fewer tokens due to low coding efficiency for modeling complex coupled information. In this paper, we propose a neural speech codec named FreeCodec which employs a more effective encoding framework by decomposing intrinsic properties of speech into different components: 1) a global vector is extracted as the timbre information, 2) a prosody encoder with a long stride level is used to model the prosody information, 3) the content information is from a content encoder. Using different training strategies, FreeCodec achieves state-of-the-art performance in reconstruction and disentanglement scenarios. Results from subjective and objective experiments demonstrate that our framework outperforms existing methods.
Abstract (translated)
URL
https://arxiv.org/abs/2412.01053
PDF
-
Complexity boosted adaptive training for better low resource ASR performance
2024-12-01 16:32:49Hongxuan Lu, Shenjian Wang, Biao LiAbstract
During the entire training process of the ASR model, the intensity of data augmentation and the approach of calculating training loss are applied in a regulated manner based on preset parameters. For example, SpecAugment employs a predefined strength of augmentation to mask parts of the time-frequency domain spectrum. Similarly, in CTC-based multi-layer models, the loss is generally determined based on the output of the encoder's final layer during the training process. However, ignoring dynamic characteristics may suboptimally train models. To address the issue, we present a two-stage training method, known as complexity-boosted adaptive (CBA) training. It involves making dynamic adjustments to data augmentation strategies and CTC loss propagation based on the complexity of the training samples. In the first stage, we train the model with intermediate-CTC-based regularization and data augmentation without any adaptive policy. In the second stage, we propose a novel adaptive policy, called MinMax-IBF, which calculates the complexity of samples. We combine the MinMax-IBF policy to data augmentation and intermediate CTC loss regularization to continue training. The proposed CBA training approach shows considerable improvements, up to 13.4% and 14.1% relative reduction in WER on the LibriSpeech 100h test-clean and test-other dataset and also up to 6.3% relative reduction on AISHELL-1 test set, over the Conformer architecture in Wenet.
Abstract (translated)
URL
https://arxiv.org/abs/2412.00877
PDF
-
Automating Feedback Analysis in Surgical Training: Detection, Categorization, and Assessment
2024-12-01 10:35:12Firdavs Nasriddinov, Rafal Kocielnik, Arushi Gupta, Cherine Yang, Elyssa Wong, Anima Anandkumar, Andrew HungAbstract
This work introduces the first framework for reconstructing surgical dialogue from unstructured real-world recordings, which is crucial for characterizing teaching tasks. In surgical training, the formative verbal feedback that trainers provide to trainees during live surgeries is crucial for ensuring safety, correcting behavior immediately, and facilitating long-term skill acquisition. However, analyzing and quantifying this feedback is challenging due to its unstructured and specialized nature. Automated systems are essential to manage these complexities at scale, allowing for the creation of structured datasets that enhance feedback analysis and improve surgical education. Our framework integrates voice activity detection, speaker diarization, and automated speech recaognition, with a novel enhancement that 1) removes hallucinations (non-existent utterances generated during speech recognition fueled by noise in the operating room) and 2) separates speech from trainers and trainees using few-shot voice samples. These aspects are vital for reconstructing accurate surgical dialogues and understanding the roles of operating room participants. Using data from 33 real-world surgeries, we demonstrated the system's capability to reconstruct surgical teaching dialogues and detect feedback instances effectively (F1 score of 0.79+/-0.07). Moreover, our hallucination removal step improves feedback detection performance by ~14%. Evaluation on downstream clinically relevant tasks of predicting Behavioral Adjustment of trainees and classifying Technical feedback, showed performances comparable to manual annotations with F1 scores of 0.82+/0.03 and 0.81+/0.03 respectively. These results highlight the effectiveness of our framework in supporting clinically relevant tasks and improving over manual methods.
Abstract (translated)
URL
https://arxiv.org/abs/2412.00760
PDF
-
Late fusion ensembles for speech recognition on diverse input audio representations
2024-12-01 10:19:24Marin Jezid\v{z}i\'c, Matej Mihel\v{c}i\'cAbstract
We explore diverse representations of speech audio, and their effect on a performance of late fusion ensemble of E-Branchformer models, applied to Automatic Speech Recognition (ASR) task. Although it is generally known that ensemble methods often improve the performance of the system even for speech recognition, it is very interesting to explore how ensembles of complex state-of-the-art models, such as medium-sized and large E-Branchformers, cope in this setting when their base models are trained on diverse representations of the input speech audio. The results are evaluated on four widely-used benchmark datasets: \textit{Librispeech, Aishell, Gigaspeech}, \textit{TEDLIUMv2} and show that improvements of $1\% - 14\%$ can still be achieved over the state-of-the-art models trained using comparable techniques on these datasets. A noteworthy observation is that such ensemble offers improvements even with the use of language models, although the gap is closing.
Abstract (translated)
URL
https://arxiv.org/abs/2412.01861
PDF
-
Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Diffusion Transformer Networks
2024-12-01 08:54:30Jiahao Cui, Hui Li, Yun Zhan, Hanlin Shang, Kaihui Cheng, Yuqi Ma, Shan Mu, Hang Zhou, Jingdong Wang, Siyu ZhuAbstract
Existing methodologies for animating portrait images face significant challenges, particularly in handling non-frontal perspectives, rendering dynamic objects around the portrait, and generating immersive, realistic backgrounds. In this paper, we introduce the first application of a pretrained transformer-based video generative model that demonstrates strong generalization capabilities and generates highly dynamic, realistic videos for portrait animation, effectively addressing these challenges. The adoption of a new video backbone model makes previous U-Net-based methods for identity maintenance, audio conditioning, and video extrapolation inapplicable. To address this limitation, we design an identity reference network consisting of a causal 3D VAE combined with a stacked series of transformer layers, ensuring consistent facial identity across video sequences. Additionally, we investigate various speech audio conditioning and motion frame mechanisms to enable the generation of continuous video driven by speech audio. Our method is validated through experiments on benchmark and newly proposed wild datasets, demonstrating substantial improvements over prior methods in generating realistic portraits characterized by diverse orientations within dynamic and immersive scenes. Further visualizations and the source code are available at: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2412.00733
PDF
-
A Comparative Study of LLM-based ASR and Whisper in Low Resource and Code Switching Scenario
2024-12-01 08:07:01Zheshu Song, Ziyang Ma, Yifan Yang, Jianheng Zhuo, Xie ChenAbstract
Large Language Models (LLMs) have showcased exceptional performance across diverse NLP tasks, and their integration with speech encoder is rapidly emerging as a dominant trend in the Automatic Speech Recognition (ASR) field. Previous works mainly concentrated on leveraging LLMs for speech recognition in English and Chinese. However, their potential for addressing speech recognition challenges in low resource settings remains underexplored. Hence, in this work, we aim to explore the capability of LLMs in low resource ASR and Mandarin-English code switching ASR. We also evaluate and compare the recognition performance of LLM-based ASR systems against Whisper model. Extensive experiments demonstrate that LLM-based ASR yields a relative gain of 12.8\% over the Whisper model in low resource ASR while Whisper performs better in Mandarin-English code switching ASR. We hope that this study could shed light on ASR for low resource scenarios.
Abstract (translated)
URL
https://arxiv.org/abs/2412.00721
PDF
