English
Related papers

Related papers: KALL-E:Autoregressive Speech Synthesis with Next-D…

200 papers

In this paper, we present a novel modeling method for single-channel multi-talker overlapped automatic speech recognition (ASR) systems. Fully neural network based end-to-end models have dramatically improved the performance of multi-taker…

Computation and Language · Computer Science 2021-07-06 Ryo Masumura , Daiki Okamura , Naoki Makishima , Mana Ihori , Akihiko Takashima , Tomohiro Tanaka , Shota Orihashi

This paper presents a generative approach to speech enhancement based on a recurrent variational autoencoder (RVAE). The deep generative speech model is trained using clean speech signals only, and it is combined with a nonnegative matrix…

Machine Learning · Computer Science 2020-02-11 Simon Leglaive , Xavier Alameda-Pineda , Laurent Girin , Radu Horaud

Multilingual end-to-end (E2E) models have shown great promise in expansion of automatic speech recognition (ASR) coverage of the world's languages. They have shown improvement over monolingual systems, and have simplified training and…

Audio and Speech Processing · Electrical Eng. & Systems 2019-09-13 Anjuli Kannan , Arindrima Datta , Tara N. Sainath , Eugene Weinstein , Bhuvana Ramabhadran , Yonghui Wu , Ankur Bapna , Zhifeng Chen , Seungji Lee

Machine Speech Chain, which integrates both end-to-end (E2E) automatic speech recognition (ASR) and text-to-speech (TTS) into one circle for joint training, has been proven to be effective in data augmentation by leveraging large amounts of…

Computation and Language · Computer Science 2021-04-09 Fengpeng Yue , Yan Deng , Lei He , Tom Ko

Audio-visual target speaker extraction (AV-TSE) models primarily rely on visual cues from the target speaker. However, humans also leverage linguistic knowledge, such as syntactic constraints, next word prediction, and prior knowledge of…

Sound · Computer Science 2025-11-11 Wenxuan Wu , Shuai Wang , Xixin Wu , Helen Meng , Haizhou Li

Incremental text-to-speech (TTS) synthesis generates utterances in small linguistic units for the sake of real-time and low-latency applications. We previously proposed an incremental TTS method that leverages a large pre-trained language…

Sound · Computer Science 2021-09-23 Takaaki Saeki , Shinnosuke Takamichi , Hiroshi Saruwatari

Non-autoregressive (NAR) text-to-speech synthesis relies on length alignment between text sequences and audio representations, constraining naturalness and expressiveness. Existing methods depend on duration modeling or pseudo-alignment…

Recent talking head synthesis works typically adopt speech features extracted from large-scale pre-trained acoustic models. However, the intrinsic many-to-many relationship between speech and lip motion causes phoneme-viseme alignment…

Graphics · Computer Science 2025-10-16 Yihuan Huang , Jiajun Liu , Yanzhen Ren , Jun Xue , Wuyang Liu , Zongkun Sun

A large part of the expressive speech synthesis literature focuses on learning prosodic representations of the speech signal which are then modeled by a prior distribution during inference. In this paper, we compare different prior…

It has been previously observed that training Variational Recurrent Autoencoders (VRAE) for text generation suffers from serious uninformative latent variables problem. The model would collapse into a plain language model that totally…

Computation and Language · Computer Science 2019-11-20 Dayiheng Liu , Xu Yang , Feng He , Yuanyuan Chen , Jiancheng Lv

Incorporating longer context has been shown to benefit machine translation, but the inclusion of context in end-to-end speech translation (E2E-ST) remains under-studied. To bridge this gap, we introduce target language context in E2E-ST,…

Computation and Language · Computer Science 2023-09-28 Amir Hussein , Brian Yan , Antonios Anastasopoulos , Shinji Watanabe , Sanjeev Khudanpur

Prior works have demonstrated zero-shot text-to-speech by using a generative language model on audio tokens obtained via a neural audio codec. It is still challenging, however, to adapt them to low-latency scenarios. In this paper, we…

Sound · Computer Science 2024-06-11 Trung Dang , David Aponte , Dung Tran , Kazuhito Koishida

End-to-end (E2E) models, which directly predict output character sequences given input speech, are good candidates for on-device speech recognition. E2E models, however, present numerous challenges: In order to be truly useful, such models…

Variational auto-encoders (VAEs) are deep generative latent variable models that can be used for learning the distribution of complex data. VAEs have been successfully used to learn a probabilistic prior over speech signals, which is then…

Sound · Computer Science 2020-12-18 Mostafa Sadeghi , Simon Leglaive , Xavier Alameda-PIneda , Laurent Girin , Radu Horaud

End-to-end Speech Translation (E2E ST) aims to directly translate source speech into target text. Existing ST methods perform poorly when only extremely small speech-text data are available for training. We observe that an ST model's…

Computation and Language · Computer Science 2023-07-10 Siqi Ouyang , Rong Ye , Lei Li

Autoregressive (AR) models with diffusion heads have recently achieved strong text-to-audio performance, yet their iterative decoding and multi-step sampling process introduce high-latency issues. To address this bottleneck, we propose a…

Speech-to-text translation (ST), which translates source language speech into target language text, has attracted intensive attention in recent years. Compared to the traditional pipeline system, the end-to-end ST model has potential…

Computation and Language · Computer Science 2019-12-17 Yuchen Liu , Jiajun Zhang , Hao Xiong , Long Zhou , Zhongjun He , Hua Wu , Haifeng Wang , Chengqing Zong

Deep generative models applied to audio have improved by a large margin the state-of-the-art in many speech and music related tasks. However, as raw waveform modelling remains an inherently difficult task, audio generative models are either…

Machine Learning · Computer Science 2021-12-16 Antoine Caillon , Philippe Esling

This paper presents the use of non-autoregressive (NAR) approaches for joint automatic speech recognition (ASR) and spoken language understanding (SLU) tasks. The proposed NAR systems employ a Conformer encoder that applies connectionist…

Audio and Speech Processing · Electrical Eng. & Systems 2023-04-24 Mohan Li , Rama Doddipatla

In this work, we present DiffVoice, a novel text-to-speech model based on latent diffusion. We propose to first encode speech signals into a phoneme-rate latent representation with a variational autoencoder enhanced by adversarial training,…

Audio and Speech Processing · Electrical Eng. & Systems 2023-04-25 Zhijun Liu , Yiwei Guo , Kai Yu
‹ Prev 1 8 9 10 Next ›