English
Related papers

Related papers: An ASR Guided Speech Intelligibility Measure for T…

200 papers

Modern text-to-speech (TTS) systems are able to generate audio that sounds almost as natural as human speech. However, the bar of developing high-quality TTS systems remains high since a sizable set of studio-quality <text, audio> pairs is…

Computation and Language · Computer Science 2019-06-19 Wei Fang , Yu-An Chung , James Glass

Sequence-to-sequence automatic speech recognition (ASR) models require large quantities of data to attain high performance. For this reason, there has been a recent surge in interest for unsupervised and semi-supervised training in such…

Audio and Speech Processing · Electrical Eng. & Systems 2019-08-21 Murali Karthick Baskar , Shinji Watanabe , Ramon Astudillo , Takaaki Hori , Lukáš Burget , Jan Černocký

In this paper, we propose a three-stage training methodology to improve the speech recognition accuracy of low-resource languages. We explore and propose an effective combination of techniques such as transfer learning, encoder freezing,…

Audio and Speech Processing · Electrical Eng. & Systems 2021-11-22 Jiyeon Kim , Mehul Kumar , Dhananjaya Gowda , Abhinav Garg , Chanwoo Kim

Transfer learning from high-resource languages is known to be an efficient way to improve end-to-end automatic speech recognition (ASR) for low-resource languages. Pre-trained or jointly trained encoder-decoder models, however, do not share…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-12 Changhan Wang , Juan Pino , Jiatao Gu

In this paper, we introduce a new and simple method for comparing speech utterances without relying on text transcripts. Our speech-to-speech comparison metric utilizes state-of-the-art speech2unit encoders like HuBERT to convert speech…

Computation and Language · Computer Science 2023-07-21 Laurent Besacier , Swen Ribeiro , Olivier Galibert , Ioan Calapodescu

Automatic Speech Recognition (ASR) is traditionally evaluated using Word Error Rate (WER), a metric that is insensitive to meaning. Embedding-based semantic metrics are better correlated with human perception, but decoder-based Large…

Recent advances in text-to-speech (TTS) have enabled models to clone arbitrary unseen speakers and synthesize high-quality, natural-sounding speech. However, evaluation methods lag behind: typical mean opinion score (MOS) estimators perform…

Audio and Speech Processing · Electrical Eng. & Systems 2025-11-25 Guansu Wang , Peijie Sun

Automatic evaluation of ST systems is typically performed by comparing translation hypotheses with one or more reference translations. While effective to some extent, this approach inherits the limitation of reference-based evaluation that…

Computation and Language · Computer Science 2026-04-09 Mauro Cettolo , Marco Gaido , Matteo Negri , Sara Papi , Luisa Bentivogli

Augmenting the training data of automatic speech recognition (ASR) systems with synthetic data generated by text-to-speech (TTS) or voice conversion (VC) has gained popularity in recent years. Several works have demonstrated improvements in…

Audio and Speech Processing · Electrical Eng. & Systems 2025-03-13 Sewade Ogun , Vincent Colotte , Emmanuel Vincent

Recent advancements in text-to-speech (TTS) have shown that language model (LM) based systems offer competitive performance compared to traditional approaches. However, in training, TTS models use ground-truth (GT) tokens as prefixes to…

Sound · Computer Science 2025-09-23 Ruonan Zhang , Lingzhou Mu , Xixin Wu , Kai Zhang

Several high-resource Text to Speech (TTS) systems currently produce natural, well-established human-like speech. In contrast, low-resource languages, including Arabic, have very limited TTS systems due to the lack of resources. We propose…

Computation and Language · Computer Science 2023-01-27 Massa Baali , Tomoki Hayashi , Hamdy Mubarak , Soumi Maiti , Shinji Watanabe , Wassim El-Hajj , Ahmed Ali

Target speaker extraction (TSE) aims to recover a target speaker's speech from a mixture using a reference utterance as a cue. Most TSE systems adopt conditional auto-encoder architectures with one-step inference. Inspired by test-time…

Sound · Computer Science 2026-03-12 Zhenghai You , Ying Shi , Lantian Li , Dong Wang

Today, many state-of-the-art automatic speech recognition (ASR) systems apply all-neural models that map audio to word sequences trained end-to-end along one global optimisation criterion in a fully data driven fashion. These models allow…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-11 Xianrui Zheng , Yulan Liu , Deniz Gunceler , Daniel Willett

Objective evaluation of synthesized speech is critical for advancing speech generation systems, yet existing metrics for intelligibility and prosody remain limited in scope and weakly correlated with human perception. Word Error Rate (WER)…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-21 Ismail Rasim Ulgen , Zongyang Du , Junchen Lu , Philipp Koehn , Berrak Sisman

We propose CONF-TSASR, a non-autoregressive end-to-end time-frequency domain architecture for single-channel target-speaker automatic speech recognition (TS-ASR). The model consists of a TitaNet based speaker embedding module, a Conformer…

Sound · Computer Science 2023-08-11 Yang Zhang , Krishna C. Puvvada , Vitaly Lavrukhin , Boris Ginsburg

Text-to-speech (TTS) acoustic models map linguistic features into an acoustic representation out of which an audible waveform is generated. The latest and most natural TTS systems build a direct mapping between linguistic and waveform…

Sound · Computer Science 2019-09-24 David Álvarez , Santiago Pascual , Antonio Bonafonte

Text-to-speech (TTS) systems are being built using end-to-end deep learning approaches. However, these systems require huge amounts of training data. We present our approach to built production quality TTS and perform speaker adaptation in…

Machine Learning · Computer Science 2023-12-05 Raviraj Joshi , Nikesh Garera

In this work, we introduce a simple yet efficient post-processing model for automatic speech recognition (ASR). Our model has Transformer-based encoder-decoder architecture which "translates" ASR model output into grammatically and…

Computation and Language · Computer Science 2019-10-24 Oleksii Hrinchuk , Mariya Popova , Boris Ginsburg

The increased adoption of digital assistants makes text-to-speech (TTS) synthesis systems an indispensable feature of modern mobile devices. It is hence desirable to build a system capable of generating highly intelligible speech in the…

Sound · Computer Science 2020-08-14 Dipjyoti Paul , Muhammed PV Shifas , Yannis Pantazis , Yannis Stylianou

The potential of synthetic data in text-to-speech (TTS) model training has gained increasing attention, yet its rationality and effectiveness require systematic validation. In this study, we systematically investigate the feasibility of…

Sound · Computer Science 2025-12-22 Tingxiao Zhou , Leying Zhang , Zhengyang Chen , Yanmin Qian