English
Related papers

Related papers: Adapting pretrained speech model for Mandarin lyri…

200 papers

Cross-lingual alignment in pretrained language models enables knowledge transfer across languages. Similar alignment has been reported in Whisper-style speech encoders, based on spoken translation retrieval using representational…

Computation and Language · Computer Science 2026-04-07 Ryan Soh-Eun Shim , Domenico De Cristofaro , Chengzhi Martin Hu , Alessandro Vietti , Barbara Plank

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

Lyrics transcription of polyphonic music is challenging because singing vocals are corrupted by the background music. To improve the robustness of lyrics transcription to the background music, we propose a strategy of combining the features…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-25 Xiaoxue Gao , Chitralekha Gupta , Haizhou Li

Although contextualized automatic speech recognition (ASR) systems are commonly used to improve the recognition of uncommon words, their effectiveness is hindered by the inherent limitations of speech-text data availability. To address this…

Sound · Computer Science 2024-06-17 Naijun Zheng , Xucheng Wan , Kai Liu , Ziqing Du , Zhou Huan

We propose a self-refining framework that enhances ASR performance with only unlabeled datasets. The process starts with an existing ASR model generating pseudo-labels on unannotated speech, which are then used to train a high-fidelity…

Computation and Language · Computer Science 2025-06-17 Cheng-Kang Chou , Chan-Jan Hsu , Ho-Lam Chung , Liang-Hsuan Tseng , Hsi-Chun Cheng , Yu-Kuan Fu , Kuan Po Huang , Hung-Yi Lee

Generating synthesised singing voice with models trained on speech data has many advantages due to the models' flexibility and controllability. However, since the information about the temporal relationship between segments and beats are…

Sound · Computer Science 2021-09-07 Cong Zhang , Jian Zhu

In this paper, we propose a novel multi-modal multi-task encoder-decoder pre-training framework (MMSpeech) for Mandarin automatic speech recognition (ASR), which employs both unlabeled speech and text data. The main difficulty in…

Multimedia · Computer Science 2022-12-02 Xiaohuan Zhou , Jiaming Wang , Zeyu Cui , Shiliang Zhang , Zhijie Yan , Jingren Zhou , Chang Zhou

Masked language models have revolutionized natural language processing systems in the past few years. A recently introduced generalization of masked language models called warped language models are trained to be more robust to the types of…

Computation and Language · Computer Science 2021-03-29 Mahdi Namazifar , John Malik , Li Erran Li , Gokhan Tur , Dilek Hakkani Tür

In Mandarin text-to-speech (TTS) system, the front-end text processing module significantly influences the intelligibility and naturalness of synthesized speech. Building a typical pipeline-based front-end which consists of multiple…

Computation and Language · Computer Science 2019-11-12 Junjie Pan , Xiang Yin , Zhiling Zhang , Shichao Liu , Yang Zhang , Zejun Ma , Yuxuan Wang

Recently, large pre-trained multilingual speech models have shown potential in scaling Automatic Speech Recognition (ASR) to many low-resource languages. Some of these models employ language adapters in their formulation, which helps to…

Computation and Language · Computer Science 2023-10-12 Atharva Kulkarni , Ajinkya Kulkarni , Miguel Couceiro , Hanan Aldarmaki

The Mandarin Chinese language is known to be strongly influenced by a rich set of regional accents, while Mandarin speech with each accent is quite low resource. Hence, an important task in Mandarin speech recognition is to appropriately…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-17 Xurong Xie , Xiang Sui , Xunying Liu , Lan Wang

Conversion of Chinese Grapheme-to-Phoneme (G2P) plays an important role in Mandarin Chinese Text-To-Speech (TTS) systems, where one of the biggest challenges is the task of polyphone disambiguation. Most of the previous polyphone…

Sound · Computer Science 2022-11-18 Chunyu Qiang , Peng Yang , Hao Che , Jinba Xiao , Xiaorui Wang , Zhongyuan Wang

To train transcriptor models that produce robust results, a large and diverse labeled dataset is required. Finding such data with the necessary characteristics is a challenging task, especially for languages less popular than English.…

Sound · Computer Science 2026-05-01 Alexandre R. Ferreira , Cláudio E. C. Campelo

Previous works on expressive speech synthesis mainly focus on current sentence. The context in adjacent sentences is neglected, resulting in inflexible speaking style for the same text, which lacks speech variations. In this paper, we…

Sound · Computer Science 2022-04-07 Shun Lei , Yixuan Zhou , Liyang Chen , Zhiyong Wu , Shiyin Kang , Helen Meng

The current lyrics transcription approaches heavily rely on supervised learning with labeled data, but such data are scarce and manual labeling of singing is expensive. How to benefit from unlabeled data and alleviate limited data problem…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-03 Xiaoxue Gao , Xianghu Yue , Haizhou Li

We show that pre-training a Transformer on music before language significantly accelerates language acquisition. Using piano performances (MAESTRO dataset), a developmental pipeline -- music $\to$ poetry $\to$ prose -- yields a $17.5\%$…

Computation and Language · Computer Science 2026-04-24 Yoshinori Nomura

Speech cloning technology is becoming more sophisticated thanks to the advances in machine learning. Researchers have successfully implemented natural-sounding English speech synthesis and good English speech cloning by some effective…

Sound · Computer Science 2022-03-08 Qingyu Xing , Xiaohan Ma

This paper presents a novel multistage fine-tuning strategy designed to enhance automatic speech recognition (ASR) performance in low-resource languages using OpenAI's Whisper model. In this approach we aim to build ASR model for languages…

Computation and Language · Computer Science 2024-11-08 Leena G Pillai , Kavya Manohar , Basil K Raju , Elizabeth Sherly

The quantity of processed data is crucial for advancing the field of singing voice synthesis. While there are tools available for lyric or note transcription tasks, they all need pre-processed data which is relatively time-consuming (e.g.,…

Sound · Computer Science 2024-10-11 Siwei Wu , Jinzheng He , Ruibin Yuan , Haojie Wei , Xipin Wei , Chenghua Lin , Jin Xu , Junyang Lin

The automated classification of stuttered speech has significant implications for timely assessments providing assistance to speech language pathologists. Despite notable advancements in the field, the cases in which multiple disfluencies…

Sound · Computer Science 2025-02-27 Huma Ameer , Seemab Latif , Mehwish Fatima