English
Related papers

Related papers: DQ-Data2vec: Decoupling Quantization for Multiling…

200 papers

While many speakers of low-resource languages regularly code-switch between their languages and other regional languages or English, datasets of codeswitched speech are too small to train bespoke acoustic models from scratch or do language…

Computation and Language · Computer Science 2023-11-28 Tolúlopé Ògúnrèmí , Christopher D. Manning , Dan Jurafsky

We propose vq-wav2vec to learn discrete representations of audio segments through a wav2vec-style self-supervised context prediction task. The algorithm uses either a gumbel softmax or online k-means clustering to quantize the dense…

Computation and Language · Computer Science 2020-02-18 Alexei Baevski , Steffen Schneider , Michael Auli

Wav2vec 2.0 is a recently proposed self-supervised framework for speech representation learning. It follows a two-stage training process of pre-training and fine-tuning, and performs well in speech recognition tasks especially ultra-low…

Sound · Computer Science 2021-01-15 Zhiyun Fan , Meng Li , Shiyu Zhou , Bo Xu

While supervised quality predictors for synthesized speech have demonstrated strong correlations with human ratings, their requirement for in-domain labeled training data hinders their generalization ability to new domains. Unsupervised…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-08 Erica Cooper , Takuma Okamoto , Yamato Ohtani , Tomoki Toda , Hisashi Kawai

We investigate the effects of post-training quantization and quantization-aware training on the generalization of Transformer language models. We present a new method called self-distilled quantization (SDQ) that minimizes accumulative…

Computation and Language · Computer Science 2023-07-13 James O' Neill , Sourav Dutta

Transformer based end-to-end modelling approaches with multiple stream inputs have been achieved great success in various automatic speech recognition (ASR) tasks. An important issue associated with such approaches is that the intermediate…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-11 Jin Li , Rongfeng Su , Xurong Xie , Nan Yan , Lan Wang

Self-supervised learning (SSL) is a powerful tool that allows learning of underlying representations from unlabeled data. Transformer based models such as wav2vec 2.0 and HuBERT are leading the field in the speech domain. Generally these…

Computation and Language · Computer Science 2022-02-08 Bethan Thomas , Samuel Kessler , Salah Karout

We introduce Wav2Seq, the first self-supervised approach to pre-train both parts of encoder-decoder models for speech data. We induce a pseudo language as a compact discrete representation, and formulate a self-supervised pseudo speech…

Computation and Language · Computer Science 2022-05-03 Felix Wu , Kwangyoun Kim , Shinji Watanabe , Kyu Han , Ryan McDonald , Kilian Q. Weinberger , Yoav Artzi

Producing a large amount of annotated speech data for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced. However, we note human babies start to learn the language by the sounds…

Computation and Language · Computer Science 2018-10-31 Yi-Chen Chen , Chia-Hao Shen , Sung-Feng Huang , Hung-yi Lee , Lin-shan Lee

Self-supervised learning (SSL) has made significant advances in speech representation learning. Models like wav2vec 2.0 and HuBERT have achieved state-of-the-art results in tasks such as speech recognition, particularly in monolingual…

Computation and Language · Computer Science 2025-09-23 María Andrea Cruz Blandón , Zakaria Aldeneh , Jie Chi , Maureen de Seyssel

Code-Switching (CS) multilingual Automatic Speech Recognition (ASR) models can transcribe speech containing two or more alternating languages during a conversation. This paper proposes (1) a new method for creating code-switching ASR…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-19 Kunal Dhawan , Dima Rekesh , Boris Ginsburg

Masked speech modeling (MSM) methods such as wav2vec2 or w2v-BERT learn representations over speech frames which are randomly masked within an utterance. While these methods improve performance of Automatic Speech Recognition (ASR) systems,…

Decoding speaker's intent is a crucial part of spoken language understanding (SLU). The presence of noise or errors in the text transcriptions, in real life scenarios make the task more challenging. In this paper, we address the spoken…

Computation and Language · Computer Science 2019-10-24 Prashanth Gurunath Shivakumar , Mu Yang , Panayiotis Georgiou

Code-switching (CS) refers to the phenomenon that languages switch within a speech signal and leads to language confusion for automatic speech recognition (ASR). This paper aims to address language confusion for improving CS-ASR from two…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-27 Hexin Liu , Haihua Xu , Leibny Paola Garcia , Andy W. H. Khong , Yi He , Sanjeev Khudanpur

Self-supervision has shown great potential for audio-visual speech recognition by vastly reducing the amount of labeled data required to build good systems. However, existing methods are either not entirely end-to-end or do not train joint…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-23 Jiachen Lian , Alexei Baevski , Wei-Ning Hsu , Michael Auli

Word vector representations enable machines to encode human language for spoken language understanding and processing. Confusion2vec, motivated from human speech production and perception, is a word vector representation which encodes…

Computation and Language · Computer Science 2022-05-04 Prashanth Gurunath Shivakumar , Panayiotis Georgiou , Shrikanth Narayanan

We show for the first time that learning powerful representations from speech audio alone followed by fine-tuning on transcribed speech can outperform the best semi-supervised methods while being conceptually simpler. wav2vec 2.0 masks the…

Computation and Language · Computer Science 2020-10-23 Alexei Baevski , Henry Zhou , Abdelrahman Mohamed , Michael Auli

Despite recent advancements in deep learning technologies, Child Speech Recognition remains a challenging task. Current Automatic Speech Recognition (ASR) models require substantial amounts of annotated data for training, which is scarce.…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-14 Rishabh Jain , Andrei Barcovschi , Mariam Yiwere , Dan Bigioi , Peter Corcoran , Horia Cucu

We present a new approach to disentangle speaker voice and phone content by introducing new components to the VQ-VAE architecture for speech synthesis. The original VQ-VAE does not generalize well to unseen speakers or content. To alleviate…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-11 Jennifer Williams , Yi Zhao , Erica Cooper , Junichi Yamagishi

With the rise of SSL and ASR technologies, the Wav2Vec2 ASR-based model has been fine-tuned for automated speech disorder quality assessment tasks, yielding impressive results and setting a new baseline for Head and Neck Cancer speech…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-14 Tuan Nguyen , Corinne Fredouille , Alain Ghio , Mathieu Balaguer , Virginie Woisard