English
Related papers

Related papers: Unspeech: Unsupervised Speech Context Embeddings

200 papers

We consider the problem of training speech recognition systems without using any labeled data, under the assumption that the learner can only access to the input utterances and a phoneme language model estimated from a non-overlapping…

Audio and Speech Processing · Electrical Eng. & Systems 2018-12-27 Chih-Kuan Yeh , Jianshu Chen , Chengzhu Yu , Dong Yu

In forensic voice comparison the speaker embedding has become widely popular in the last 10 years. Most of the pretrained speaker embeddings are trained on English corpora, because it is easily accessible. Thus, language dependency can be…

Sound · Computer Science 2023-04-12 Dávid Sztahó , Attila Fejes

Target speaker extraction aims to separate the voice of a specific speaker from mixed speech. Traditionally, this process has relied on extracting a speaker embedding from a reference speech, in which a speaker recognition model is…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-21 Bang Zeng , Ming Li

Speaker embeddings carry valuable emotion-related information, which makes them a promising resource for enhancing speech emotion recognition (SER), especially with limited labeled data. Traditionally, it has been assumed that emotion…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-03 Ismail Rasim Ulgen , Zongyang Du , Carlos Busso , Berrak Sisman

This paper presents an improved deep embedding learning method based on convolutional neural network (CNN) for text-independent speaker verification. Two improvements are proposed for x-vector embedding learning: (1) Multi-scale convolution…

Audio and Speech Processing · Electrical Eng. & Systems 2020-01-15 Bin Gu , Wu Guo

This paper aims to improve the widely used deep speaker embedding x-vector model. We propose the following improvements: (1) a hybrid neural network structure using both time delay neural network (TDNN) and long short-term memory neural…

Computation and Language · Computer Science 2019-02-22 Yun Tang , Guohong Ding , Jing Huang , Xiaodong He , Bowen Zhou

Many speech processing tasks involve measuring the acoustic similarity between speech segments. Acoustic word embeddings (AWE) allow for efficient comparisons by mapping speech segments of arbitrary duration to fixed-dimensional vectors.…

Computation and Language · Computer Science 2020-12-15 Lisa van Staden , Herman Kamper

Stance detection is an important task, supporting many downstream tasks such as discourse parsing and modeling the propagation of fake news, rumors, and science denial. In this paper, we propose a novel framework for stance detection. Our…

Computation and Language · Computer Science 2021-12-21 Ron Korenblum Pick , Vladyslav Kozhukhov , Dan Vilenchik , Oren Tsur

Recently, sequence-to-sequence models with attention have been successfully applied in Text-to-speech (TTS). These models can generate near-human speech with a large accurately-transcribed speech corpus. However, preparing such a large…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-12 Haitong Zhang , Yue Lin

Acoustic word embeddings are typically created by training a pooling function using pairs of word-like units. For unsupervised systems, these are mined using k-nearest neighbor (KNN) search, which is slow. Recently, mean-pooled…

Computation and Language · Computer Science 2023-06-06 Ramon Sanabria , Ondrej Klejch , Hao Tang , Sharon Goldwater

We propose to learn acoustic word embeddings with temporal context for query-by-example (QbE) speech search. The temporal context includes the leading and trailing word sequences of a word. We assume that there exist spoken word pairs in…

Computation and Language · Computer Science 2018-06-19 Yougen Yuan , Cheung-Chi Leung , Lei Xie , Hongjie Chen , Bin Ma , Haizhou Li

Unseen data conditions can inflict serious performance degradation on systems relying on supervised machine learning algorithms. Because data can often be unseen, and because traditional machine learning algorithms are trained in a…

Machine Learning · Computer Science 2017-09-01 Vikramjit Mitra , Horacio Franco

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

For conversational large-vocabulary continuous speech recognition (LVCSR) tasks, up to about two thousand hours of audio is commonly used to train state of the art models. Collection of labeled conversational audio however, is prohibitively…

Computation and Language · Computer Science 2017-05-30 Shane Walker , Morten Pedersen , Iroro Orife , Jason Flaks

In this paper, we propose a simple but powerful unsupervised learning method for speaker recognition, namely Contrastive Equilibrium Learning (CEL), which increases the uncertainty on nuisance factors latent in the embeddings by employing…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-23 Sung Hwan Mun , Woo Hyun Kang , Min Hyun Han , Nam Soo Kim

Recently, end-to-end multi-speaker text-to-speech (TTS) systems gain success in the situation where a lot of high-quality speech plus their corresponding transcriptions are available. However, laborious paired data collection processes…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-05 Tao Tu , Yuan-Jui Chen , Alexander H. Liu , Hung-yi Lee

Self-supervised learning (SSL) methods which learn representations of data without explicit supervision have gained popularity in speech-processing tasks, particularly for single-talker applications. However, these models often have…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-02 Zili Huang , Desh Raj , Paola García , Sanjeev Khudanpur

Over the recent years, various deep learning-based methods were proposed for extracting a fixed-dimensional embedding vector from speech signals. Although the deep learning-based embedding extraction methods have shown good performance in…

Audio and Speech Processing · Electrical Eng. & Systems 2021-12-08 Woo Hyun Kang , Jahangir Alam , Abderrahim Fathan

Sentence representation at the semantic level is a challenging task for Natural Language Processing and Artificial Intelligence. Despite the advances in word embeddings (i.e. word vector representations), capturing sentence meaning is an…

This paper proposes a speech rhythm-based method for speaker embeddings to model phoneme duration using a few utterances by the target speaker. Speech rhythm is one of the essential factors among speaker characteristics, along with acoustic…

Sound · Computer Science 2024-02-13 Kenichi Fujita , Atsushi Ando , Yusuke Ijima