English
Related papers

Related papers: FastS2S-VC: Streaming Non-Autoregressive Sequence-…

200 papers

Non-autoregressive (NAR) models for automatic speech recognition (ASR) aim to achieve high accuracy and fast inference by simplifying the autoregressive (AR) generation process of conventional models. Connectionist temporal classification…

Audio and Speech Processing · Electrical Eng. & Systems 2024-03-29 Yuya Fujita , Shinji Watanabe , Xuankai Chang , Takashi Maekaku

Voice Conversion (VC) is a technique that aims to transform the non-linguistic information of a source utterance to change the perceived identity of the speaker. While there is a rich literature on VC, most proposed methods are trained and…

Having a sequence-to-sequence model which can operate in an online fashion is important for streaming applications such as Voice Search. Neural transducer is a streaming sequence-to-sequence model, but has shown a significant degradation in…

Computation and Language · Computer Science 2017-12-06 Tara N. Sainath , Chung-Cheng Chiu , Rohit Prabhavalkar , Anjuli Kannan , Yonghui Wu , Patrick Nguyen , Zhifeng Chen

The autoregressive (AR) models, such as attention-based encoder-decoder models and RNN-Transducer, have achieved great success in speech recognition. They predict the output sequence conditioned on the previous tokens and acoustic encoded…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-06 Zhengkun Tian , Jiangyan Yi , Jianhua Tao , Ye Bai , Shuai Zhang , Zhengqi Wen , Xuefei Liu

We present an unsupervised non-parallel many-to-many voice conversion (VC) method using a generative adversarial network (GAN) called StarGAN v2. Using a combination of adversarial source classifier loss and perceptual loss, our model…

Sound · Computer Science 2021-07-26 Yinghao Aaron Li , Ali Zare , Nima Mesgarani

Cross-lingual voice conversion (VC) is a task that aims to synthesize target voices with the same content while source and target speakers speak in different languages. Its challenge lies in the fact that the source and target data are…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-01 Che-Jui Chang

Conventional automatic speech recognition (ASR) typically performs multi-level pattern recognition tasks that map the acoustic speech waveform into a hierarchy of speech units. But, it is widely known that information loss in the earlier…

Computation and Language · Computer Science 2017-09-25 Andros Tjandra , Sakriani Sakti , Satoshi Nakamura

Although attention based end-to-end models have achieved promising performance in speech recognition, the multi-pass forward computation in beam-search increases inference time cost, which limits their practical applications. To address…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-07 Ye Bai , Jiangyan Yi , Jianhua Tao , Zhengkun Tian , Zhengqi Wen , Shuai Zhang

Voice conversion (VC) techniques aim to modify speaker identity of an utterance while preserving the underlying linguistic information. Most VC approaches ignore modeling of the speaking style (e.g. emotion and emphasis), which may contain…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-20 Songxiang Liu , Yuewen Cao , Shiyin Kang , Na Hu , Xunying Liu , Dan Su , Dong Yu , Helen Meng

The Transformer self-attention network has shown promising performance as an alternative to recurrent neural networks in end-to-end (E2E) automatic speech recognition (ASR) systems. However, Transformer has a drawback in that the entire…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-19 Emiru Tsunoo , Yosuke Kashiwagi , Shinji Watanabe

Simultaneous speech translation (SST) outputs translations in parallel with streaming speech input, balancing translation quality and latency. While large language models (LLMs) have been extended to handle the speech modality, streaming…

Computation and Language · Computer Science 2025-04-23 Keqi Deng , Wenxi Chen , Xie Chen , Philip C. Woodland

Automatic Speech Recognition (ASR) has seen remarkable progress, with models like OpenAI Whisper and NVIDIA Canary achieving state-of-the-art (SOTA) performance in offline transcription. However, these models are not designed for streaming…

Computation and Language · Computer Science 2026-04-07 Tomer Krichli , Bhiksha Raj , Joseph Keshet

Zero-shot voice conversion (VC) aims to transfer the timbre from the source speaker to an arbitrary unseen speaker while preserving the original linguistic content. Despite recent advancements in zero-shot VC using language model-based or…

Audio and Speech Processing · Electrical Eng. & Systems 2024-12-11 Jixun Yao , Yuguang Yang , Yu Pan , Ziqian Ning , Jiaohao Ye , Hongbin Zhou , Lei Xie

In this work, we propose a streaming AV-ASR system based on a hybrid connectionist temporal classification (CTC)/attention neural network architecture. The audio and the visual encoder neural networks are both based on the conformer…

Audio and Speech Processing · Electrical Eng. & Systems 2023-07-04 Pingchuan Ma , Niko Moritz , Stavros Petridis , Christian Fuegen , Maja Pantic

Audio-visual automatic speech recognition is a promising approach to robust ASR under noisy conditions. However, up until recently it had been traditionally studied in isolation assuming the video of a single speaking face matches the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-05-13 Otavio Braga , Olivier Siohan

Voice Conversion (VC) emerged as a significant domain of research in the field of speech synthesis in recent years due to its emerging application in voice-assisting technology, automated movie dubbing, and speech-to-singing conversion to…

Sound · Computer Science 2021-04-27 Sandipan Dhar , Nanda Dulal Jana , Swagatam Das

Attention-based sequence-to-sequence models have shown promising results in automatic speech recognition. Using these architectures, one-dimensional input and output sequences are related by an attention approach, thereby replacing more…

Computation and Language · Computer Science 2019-11-21 Parnia Bahar , Albert Zeyer , Ralf Schlüter , Hermann Ney

This paper proposes singing voice synthesis (SVS) based on frame-level sequence-to-sequence models considering vocal timing deviation. In SVS, it is essential to synchronize the timing of singing with temporal structures represented by…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-23 Miku Nishihara , Yukiya Hono , Kei Hashimoto , Yoshihiko Nankaku , Keiichi Tokuda

Recently, voice conversion (VC) has been widely studied. Many VC systems use disentangle-based learning techniques to separate the speaker and the linguistic content information from a speech signal. Subsequently, they convert the voice by…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-03 Yen-Hao Chen , Da-Yi Wu , Tsung-Han Wu , Hung-yi Lee

Non-parallel many-to-many voice conversion remains an interesting but challenging speech processing task. Many style-transfer-inspired methods such as generative adversarial networks (GANs) and variational autoencoders (VAEs) have been…

Audio and Speech Processing · Electrical Eng. & Systems 2020-04-17 Kaizhi Qian , Zeyu Jin , Mark Hasegawa-Johnson , Gautham J. Mysore