English
Related papers

Related papers: Kanade: A Simple Disentangled Tokenizer for Spoken…

200 papers

For speaker recognition, it is difficult to extract an accurate speaker representation from speech because of its mixture of speaker traits and content. This paper proposes a disentanglement framework that simultaneously models speaker…

Audio and Speech Processing · Electrical Eng. & Systems 2023-11-02 Tianchi Liu , Kong Aik Lee , Qiongqiong Wang , Haizhou Li

As a cornerstone in language modeling, tokenization involves segmenting text inputs into pre-defined atomic units. Conventional statistical tokenizers often disrupt constituent boundaries within words, thereby corrupting semantic…

Computation and Language · Computer Science 2025-07-11 Qingyang Zhu , Xiang Hu , Pengyu Ji , Wei Wu , Kewei Tu

Generating speech across different accents while preserving speaker identity is crucial for various real-world applications. However, accurately and independently modeling both speaker and accent characteristics in text-to-speech (TTS)…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-03 Xuehao Zhou , Mingyang Zhang , Yi Zhou , Zhizheng Wu , Haizhou Li

Modern tokenizers employ deterministic algorithms to map text into a single "canonical" token sequence, yet the same string can be encoded as many non-canonical tokenizations using the tokenizer vocabulary. In this work, we investigate the…

Computation and Language · Computer Science 2026-02-04 Brian Siyuan Zheng , Alisa Liu , Orevaoghene Ahia , Jonathan Hayase , Yejin Choi , Noah A. Smith

In order to build language technologies for majority of the languages, it is important to leverage the resources available in public domain on the internet - commonly referred to as `Found Data'. However, such data is characterized by the…

Audio and Speech Processing · Electrical Eng. & Systems 2019-09-27 Nishant Gurunath , Sai Krishna Rallabandi , Alan Black

Recent advancements in neural audio codecs have enabled the use of tokenized audio representations in various audio generation tasks, such as text-to-speech, text-to-audio, and text-to-music generation. Leveraging this approach, we propose…

Sound · Computer Science 2025-02-14 Kyungsu Kim , Junghyun Koo , Sungho Lee , Haesun Joung , Kyogu Lee

Enhancing small language models for real-life application deployment is a significant challenge facing the research community. Due to the difficulties and costs of using large language models, researchers are seeking ways to effectively…

Computation and Language · Computer Science 2024-09-20 Mohamad Ballout , Ulf Krumnack , Gunther Heidemann , Kai-Uwe Kühnberger

Compositional generalization is a basic mechanism in human language learning, which current neural networks struggle with. A recently proposed Disentangled sequence-to-sequence model (Dangle) shows promising generalization capability by…

Computation and Language · Computer Science 2022-12-13 Hao Zheng , Mirella Lapata

Voice Conversion (VC) converts the voice of a source speech to that of a target while maintaining the source's content. Speech can be mainly decomposed into four components: content, timbre, rhythm and pitch. Unfortunately, most related…

Sound · Computer Science 2023-06-22 Zhonghua Liu , Shijun Wang , Ning Chen

Generally speaking, the main objective when training a neural speech synthesis system is to synthesize natural and expressive speech from the output layer of the neural network without much attention given to the hidden layers. However, by…

Sound · Computer Science 2021-06-28 Hieu-Thi Luong , Junichi Yamagishi

Dialogue disentanglement aims to detach the chronologically ordered utterances into several independent sessions. Conversation utterances are essentially organized and described by the underlying discourse, and thus dialogue disentanglement…

Computation and Language · Computer Science 2023-06-13 Bobo Li , Hao Fei , Fei Li , Shengqiong Wu , Lizi Liao , Yinwei Wei , Tat-Seng Chua , Donghong Ji

Recently, sequence-to-sequence (seq-to-seq) models have been successfully applied in text-to-speech (TTS) to synthesize speech for single-language text. To synthesize speech for multiple languages usually requires multi-lingual speech from…

Sound · Computer Science 2022-11-18 Haitong Zhang , Yue Lin

We study speech language models that incorporate semantic initialization and planning losses to achieve robust and consistent generation. Our approach initializes speech tokens with self-supervised features, applies a light alignment loss,…

Computation and Language · Computer Science 2025-10-01 Morteza Rohanian , Michael Krauthammer

This paper presents a novel design of neural network system for fine-grained style modeling, transfer and prediction in expressive text-to-speech (TTS) synthesis. Fine-grained modeling is realized by extracting style embeddings from the…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-11 Daxin Tan , Tan Lee

In this paper, we present SANE-TTS, a stable and natural end-to-end multilingual TTS model. By the difficulty of obtaining multilingual corpus for given speaker, training multilingual TTS model with monolingual corpora is unavoidable. We…

Audio and Speech Processing · Electrical Eng. & Systems 2022-09-28 Hyunjae Cho , Wonbin Jung , Junhyeok Lee , Sang Hoon Woo

In this paper we aim to automatically discover high quality frame-level speech features and acoustic tokens directly from unlabeled speech data. A Multi-granular Acoustic Tokenizer (MAT) was proposed for automatic discovery of multiple sets…

Computation and Language · Computer Science 2017-07-19 Cheng-Tao Chung , Cheng-Yu Tsai , Chia-Hsiang Liu , Lin-Shan Lee

Recently end-to-end neural audio/speech coding has shown its great potential to outperform traditional signal analysis based audio codecs. This is mostly achieved by following the VQ-VAE paradigm where blind features are learned,…

Sound · Computer Science 2023-02-28 Xue Jiang , Xiulian Peng , Yuan Zhang , Yan Lu

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

We introduce a deep learning model for speech denoising, a long-standing challenge in audio analysis arising in numerous applications. Our approach is based on a key observation about human speech: there is often a short pause between each…

Sound · Computer Science 2020-10-26 Ruilin Xu , Rundi Wu , Yuko Ishiwaka , Carl Vondrick , Changxi Zheng

Recent progress in Spoken Language Modeling has shown that learning language directly from speech is feasible. Generating speech through a pipeline that operates at the text level typically loses nuances, intonations, and non-verbal…

Computation and Language · Computer Science 2024-10-31 Maxime Poli , Emmanuel Chemla , Emmanuel Dupoux