English
Related papers

Related papers: TalTech Systems for the Interspeech 2025 ML-SUPERB…

200 papers

We present a masked diffusion language modeling framework for data-efficient training for the BabyLM 2025 Challenge. Our approach applies diffusion training objectives to language modeling under strict data constraints, incorporating…

Computation and Language · Computer Science 2025-09-08 Despoina Kosmopoulou , Efthymios Georgiou , Vaggelis Dorovatas , Georgios Paraskevopoulos , Alexandros Potamianos

Speech language models (SpeechLMs) accept speech input and produce speech output, allowing for more natural human-computer interaction compared to text-based large language models (LLMs). Traditional approaches for developing SpeechLMs are…

Computation and Language · Computer Science 2024-12-03 Aohan Zeng , Zhengxiao Du , Mingdao Liu , Lei Zhang , Shengmin Jiang , Yuxiao Dong , Jie Tang

Text language models have shown remarkable zero-shot capability in generalizing to unseen tasks when provided with well-formulated instructions. However, existing studies in speech processing primarily focus on limited or specific tasks.…

The goal of this paper is to learn robust speaker representation for bilingual speaking scenario. The majority of the world's population speak at least two languages; however, most speaker recognition systems fail to recognise the same…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-08 Kihyun Nam , Youkyum Kim , Jaesung Huh , Hee Soo Heo , Jee-weon Jung , Joon Son Chung

This paper presents our MSXF TTS system for Task 3.1 of the Audio Deep Synthesis Detection (ADD) Challenge 2022. We use an end to end text to speech system, and add a constraint loss to the system when training stage. The end to end TTS…

Sound · Computer Science 2022-01-28 Chunyong Yang , Pengfei Liu , Yanli Chen , Hongbin Wang , Min Liu

Speaker identification systems in a real-world scenario are tasked to identify a speaker amongst a set of enrolled speakers given just a few samples for each enrolled speaker. This paper demonstrates the effectiveness of meta-learning and…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-25 Ashutosh Chaubey , Sparsh Sinha , Susmita Ghose

Self-supervised learning (SSL) speech models, which can serve as powerful upstream models to extract meaningful speech representations, have achieved unprecedented success in speech representation learning. However, their effectiveness on…

Sound · Computer Science 2023-02-01 Tung-Yu Wu , Chen-An Li , Tzu-Han Lin , Tsu-Yuan Hsu , Hung-Yi Lee

We introduce a novel suite of state-of-the-art bilingual text embedding models that are designed to support English and another target language. These models are capable of processing lengthy text inputs with up to 8192 tokens, making them…

Modeling voices for multiple speakers and multiple languages in one text-to-speech system has been a challenge for a long time. This paper presents an extension on Tacotron2 to achieve bilingual multispeaker speech synthesis when there are…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-22 Zexin Cai , Yaogen Yang , Ming Li

Self-supervised learned (SSL) models such as Wav2vec and HuBERT yield state-of-the-art results on speech-related tasks. Given the effectiveness of such models, it is advantageous to use them in conventional ASR systems. While some…

Computation and Language · Computer Science 2024-04-22 Darshan Prabhu , Sai Ganesh Mirishkar , Pankaj Wasnik

In recent years, neural models learned through self-supervised pretraining on large scale multilingual text or speech data have exhibited promising results for underresourced languages, especially when a relatively large amount of data from…

Computation and Language · Computer Science 2023-01-19 Karol Nowakowski , Michal Ptaszynski , Kyoko Murasaki , Jagna Nieuważny

While the last decade has witnessed significant advancements in Automatic Speech Recognition (ASR) systems, performance of these systems for individuals with speech disabilities remains inadequate, partly due to limited public training…

Language diversity presents a significant challenge in speech-to-text (S2T) tasks, such as automatic speech recognition and translation. Traditional multi-lingual multi-task training approaches aim to address this by jointly optimising…

Sound · Computer Science 2025-07-09 Qiuming Zhao , Guangzhi Sun , Chao Zhang

We present a model of text analysis for text-to-speech (TTS) synthesis based on (weighted) finite-state transducers, which serves as the text-analysis module of the multilingual Bell Labs TTS system. The transducers are constructed using a…

cmp-lg · Computer Science 2008-02-03 Richard Sproat

Advent of modern deep learning techniques has given rise to advancements in the field of Speech Emotion Recognition (SER). However, most systems prevalent in the field fail to generalize to speakers not seen during training. This study…

Computation and Language · Computer Science 2024-06-21 Arnav Goel , Medha Hira , Anubha Gupta

We present the DKU system for Task 2 of the MLC-SLM Challenge, which aims to perform multi-speaker automatic speech recognition directly from raw audio without Oracle speaker labels or time boundaries. Our approach builds upon a…

Audio and Speech Processing · Electrical Eng. & Systems 2025-07-15 Yuke Lin , Ming Cheng , Ze Li , Ming Li

Recent advances in sophisticated synthetic speech generated from text-to-speech (TTS) or voice conversion (VC) systems cause threats to the existing automatic speaker verification (ASV) systems. Since such synthetic speech is generated from…

Audio and Speech Processing · Electrical Eng. & Systems 2022-12-15 Youngsik Eom , Yeonghyeon Lee , Ji Sub Um , Hoirin Kim

Sequence-to-sequence (seq2seq) models are competitive with hybrid models for automatic speech recognition (ASR) tasks when large amounts of training data are available. However, data sparsity and domain adaptation are more problematic for…

Computation and Language · Computer Science 2021-06-16 Chak-Fai Li , Francis Keith , William Hartmann , Matthew Snover , Owen Kimball

Automatic speech recognition (ASR) of single channel far-field recordings with an unknown number of speakers is traditionally tackled by cascaded modules. Recent research shows that end-to-end (E2E) multi-speaker ASR models can achieve…

Audio and Speech Processing · Electrical Eng. & Systems 2022-02-11 Ilya Sklyar , Anna Piunova , Xianrui Zheng , Yulan Liu

This paper proposes a zero-shot text-to-speech (TTS) conditioned by a self-supervised speech-representation model acquired through self-supervised learning (SSL). Conventional methods with embedding vectors from x-vector or global style…

Sound · Computer Science 2023-12-19 Kenichi Fujita , Takanori Ashihara , Hiroki Kanagawa , Takafumi Moriya , Yusuke Ijima