English
Related papers

Related papers: Speech Tokenizer is Key to Consistent Representati…

200 papers

Voice anonymisation can be used to help protect speaker privacy when speech data is shared with untrusted others. In most practical applications, while the voice identity should be sanitised, other attributes such as the spoken content…

Audio and Speech Processing · Electrical Eng. & Systems 2024-08-09 Michele Panariello , Massimiliano Todisco , Nicholas Evans

Self-supervised pre-training has been successful in both text and speech processing. Speech and text offer different but complementary information. The question is whether we are able to perform a speech-text joint pre-training on unpaired…

Computation and Language · Computer Science 2022-11-01 Xianghu Yue , Junyi Ao , Xiaoxue Gao , Haizhou Li

Neural Speech Codecs face a fundamental trade-off at low bitrates: preserving acoustic fidelity often compromises semantic richness. To address this, we introduce SACodec, a novel codec built upon an asymmetric dual-quantizer that employs…

Sound · Computer Science 2025-12-25 Zhongren Dong , Bin Wang , Jing Han , Haotian Guo , Xiaojun Mo , Yimin Cao , Zixing Zhang

Bitrate scalability is a desirable feature for audio coding in real-time communications. Existing neural audio codecs usually enforce a specific bitrate during training, so different models need to be trained for each target bitrate, which…

Sound · Computer Science 2022-07-08 Xue Jiang , Xiulian Peng , Huaying Xue , Yuan Zhang , Yan Lu

In recent years, advancements in representation learning and language models have propelled Automated Captioning (AC) to new heights, enabling the generation of human-level descriptions. Leveraging these advancements, we propose AVCap, an…

Audio and Speech Processing · Electrical Eng. & Systems 2024-07-12 Jongsuk Kim , Jiwon Shin , Junmo Kim

Tokenization is a foundational step in natural language processing (NLP) tasks, bridging raw text and language models. Existing tokenization approaches like Byte-Pair Encoding (BPE) originate from the field of data compression, and it has…

Computation and Language · Computer Science 2024-10-08 Craig W. Schmidt , Varshini Reddy , Haoran Zhang , Alec Alameddine , Omri Uzan , Yuval Pinter , Chris Tanner

The goal of voice conversion (VC) is to convert input voice to match the target speaker's voice while keeping text and prosody intact. VC is usually used in entertainment and speaking-aid systems, as well as applied for speech data…

Sound · Computer Science 2022-04-01 A. Kashkin , I. Karpukhin , S. Shishkin

The speech tokenizer plays a crucial role in recent speech tasks, generally serving as a bridge between speech signals and language models. While low-frame-rate codecs are widely employed as speech tokenizers, the impact of frame rates on…

Computation and Language · Computer Science 2025-06-16 Haoyang Zhang , Hexin Liu , Xiangyu Zhang , Qiquan Zhang , Yuchen Hu , Junqi Zhao , Fei Tian , Xuerui Yang , Leibny Paola Garcia , Eng Siong Chng

How to boost speech pre-training with textual data is an unsolved problem due to the fact that speech and text are very different modalities with distinct characteristics. In this paper, we propose a cross-modal Speech and Language Model…

Computation and Language · Computer Science 2023-06-16 Ziqiang Zhang , Sanyuan Chen , Long Zhou , Yu Wu , Shuo Ren , Shujie Liu , Zhuoyuan Yao , Xun Gong , Lirong Dai , Jinyu Li , Furu Wei

Discrete audio tokens derived from self-supervised learning models have gained widespread usage in speech generation. However, current practice of directly utilizing audio tokens poses challenges for sequence modeling due to the length of…

Sound · Computer Science 2024-01-17 Feiyu Shen , Yiwei Guo , Chenpeng Du , Xie Chen , Kai Yu

Neural audio codecs (NACs), which use neural networks to generate compact audio representations, have garnered interest for their applicability to many downstream tasks -- especially quantized codecs due to their compatibility with large…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-13 Ryo Aihara , Yoshiki Masuyama , Gordon Wichern , François G. Germain , Jonathan Le Roux

Most of the prevalent approaches in speech prosody modeling rely on learning global style representations in a continuous latent space which encode and transfer the attributes of reference speech. However, recent work on neural codecs which…

Voice conversion is a task of synthesizing an utterance with target speaker's voice while maintaining linguistic information of the source utterance. While a speaker can produce varying utterances from a single script with different…

Sound · Computer Science 2025-04-17 Soobin Suh , Dabi Ahn , Heewoong Park , Jonghun Park

We propose using self-supervised discrete representations for the task of speech resynthesis. To generate disentangled representation, we separately extract low-bitrate representations for speech content, prosodic information, and speaker…

Sequence-to-sequence (seq2seq) voice conversion (VC) models are attractive owing to their ability to convert prosody. Nonetheless, without sufficient data, seq2seq VC models can suffer from unstable training and mispronunciation problems in…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-10 Wen-Chin Huang , Tomoki Hayashi , Yi-Chiao Wu , Hirokazu Kameoka , Tomoki Toda

Speech signals are inherently complex as they encompass both global acoustic characteristics and local semantic information. However, in the task of target speech extraction, certain elements of global and local semantic information in the…

Sound · Computer Science 2024-08-27 Zhaoxi Mu , Xinyu Yang , Sining Sun , Qing Yang

Word vector representations are a crucial part of Natural Language Processing (NLP) and Human Computer Interaction. In this paper, we propose a novel word vector representation, Confusion2Vec, motivated from the human speech production and…

Computation and Language · Computer Science 2019-07-01 Prashanth Gurunath Shivakumar , Panayiotis Georgiou

One-shot voice conversion has received significant attention since only one utterance from source speaker and target speaker respectively is required. Moreover, source speaker and target speaker do not need to be seen during training.…

Sound · Computer Science 2021-06-22 Hongqiang Du , Lei Xie

Speech emotion conversion is the task of modifying the perceived emotion of a speech utterance while preserving the lexical content and speaker identity. In this study, we cast the problem of emotion conversion as a spoken language…

The process of reconstructing missing parts of speech audio from context is called speech in-painting. Human perception of speech is inherently multi-modal, involving both audio and visual (AV) cues. In this paper, we introduce and study a…

Multimedia · Computer Science 2024-06-04 Mahsa Kadkhodaei Elyaderani , Shahram Shirani