English
Related papers

Related papers: Towards Leveraging Sequential Structure in Animal …

200 papers

Discrete audio representations, termed audio tokens, are broadly categorized into semantic and acoustic tokens, typically generated through unsupervised tokenization of continuous audio representations. However, their applicability to…

Sound · Computer Science 2025-05-22 Jingguang Tian , Haoqin Sun , Xinhui Hu , Xinkang Xu

Modern speaker recognition systems represent utterances by embedding vectors. Conventional embedding vectors are dense and non-structural. In this paper, we propose an ordered binary embedding approach that sorts the dimensions of the…

Sound · Computer Science 2023-05-26 Jiaying Wang , Xianglong Wang , Namin Wang , Lantian Li , Dong Wang

Recent success in speech representation learning enables a new way to leverage unlabeled data to train speech recognition model. In speech representation learning, a large amount of unlabeled data is used in a self-supervised manner to…

Audio and Speech Processing · Electrical Eng. & Systems 2020-12-15 Shaoshi Ling , Yuzong Liu

With advances in deep learning, neural network based speech enhancement (SE) has developed rapidly in the last decade. Meanwhile, the self-supervised pre-trained model and vector quantization (VQ) have achieved excellent performance on many…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-17 Xiao-Ying Zhao , Qiu-Shi Zhu , Jie Zhang

Over the recent years, various deep learning-based embedding methods have been proposed and have shown impressive performance in speaker verification. However, as in most of the classical embedding techniques, the deep learning-based…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-10 Woo Hyun Kang , Sung Hwan Mun , Min Hyun Han , Nam Soo Kim

Identifying multiple speakers without knowing where a speaker's voice is in a recording is a challenging task. In this paper, a hierarchical attention network is proposed to solve a weakly labelled speaker identification problem. The use of…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-28 Yanpei Shi , Qiang Huang , Thomas Hain

Speaker recognition systems based on deep speaker embeddings have achieved significant performance in controlled conditions according to the results obtained for early NIST SRE (Speaker Recognition Evaluation) datasets. From the practical…

Recently, deep architectures, such as recurrent and recursive neural networks have been successfully applied to various natural language processing tasks. Inspired by bidirectional recurrent neural networks which use representations that…

Machine Learning · Computer Science 2013-12-03 Ozan İrsoy , Claire Cardie

Self-supervised learning (SSL) models such as Wav2Vec 2.0 and HuBERT have shown remarkable success in extracting phonetic information from raw audio without labelled data. While prior work has demonstrated that SSL embeddings encode…

Sound · Computer Science 2025-07-10 Anastasia Ananeva , Anton Tomilov , Marina Volkova

Most speech recognition tasks pertain to mapping words across two modalities: acoustic and orthographic. In this work, we suggest learning encoders that map variable-length, acoustic or phonetic, sequences that represent words into…

Machine Learning · Computer Science 2019-08-02 Mohamed El-Geish

Self-supervised speech representation learning has become essential for extracting meaningful features from untranscribed audio. Recent advances highlight the potential of deriving discrete symbols from the features correlated with…

Computation and Language · Computer Science 2024-09-17 Ryota Komatsu , Takahiro Shinozaki

Self-supervised learning has been used to leverage unlabelled data, improving accuracy and generalisation of speech systems through the training of representation models. While many recent works have sought to produce effective…

Computation and Language · Computer Science 2023-10-18 Antoni Dimitriadis , Siqi Pan , Vidhyasaharan Sethu , Beena Ahmed

Both speech and sensor time series data encode information in both the time- and frequency- domains, like spectral powers and waveform shapelets. We show that speech foundation models learn representations that generalize beyond the speech…

Machine Learning · Computer Science 2025-11-25 Jaya Narain , Zakaria Aldeneh , Shirley Ren

Is there a foreign language describing protein sequences and structures simultaneously? Protein structures, represented by continuous 3D points, have long posed a challenge due to the contrasting modeling paradigms of discrete sequences. We…

Biomolecules · Quantitative Biology 2024-03-20 Zhangyang Gao , Cheng Tan , Jue Wang , Yufei Huang , Lirong Wu , Stan Z. Li

Neural latent variable models enable the discovery of interesting structure in speech audio data. This paper presents a comparison of two different approaches which are broadly based on predicting future time-steps or auto-encoding the…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-28 Henry Zhou , Alexei Baevski , Michael Auli

Language models require tokenized inputs. However, tokenization strategies for continuous data like audio and vision are often based on simple heuristics such as fixed sized convolutions or discrete clustering, which do not necessarily…

Computation and Language · Computer Science 2024-10-08 Alan Baade , Puyuan Peng , David Harwath

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

We propose an approach for training speaker identification models in a weakly supervised manner. We concentrate on the setting where the training data consists of a set of audio recordings and the speaker annotation is provided only at the…

Sound · Computer Science 2018-06-25 Martin Karu , Tanel Alumäe

Zero-resource word segmentation and clustering systems aim to tokenise speech into word-like units without access to text labels. Despite progress, the induced lexicons are still far from perfect. In an idealised setting with gold word…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-28 Danel Slabbert , Simon Malan , Herman Kamper

Self-supervised speech models (S3Ms) are known to encode rich phonetic information, yet how this information is structured remains underexplored. We conduct a comprehensive study across 96 languages to analyze the underlying structure of…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-15 Kwanghee Choi , Eunjung Yeo , Cheol Jun Cho , David Harwath , David R. Mortensen