paper-with-me

Papers

Diagonal State Space Augmented Transformers for Speech Recognition

2023-02-27 · George Saon, Ankit Gupta, Xiaodong Cui

We improve on the popular conformer architecture by replacing the depthwise temporal convolutions with diagonal state space (DSS) models. DSS is a recently introduced variant of linear RNNs obtained by discretizing a linear dynamical system with a diagonal state transition matrix. DSS layers project the input sequence onto a space of orthogonal polynomials where the choice of basis functions, metric and support is controlled by the eigenvalues of the transition matrix. We compare neural transducers with either conformer or our proposed DSS-augmented transformer (DSSformer) encoders on three public corpora: Switchboard English conversational telephone speech 300 hours, Switchboard+Fisher 2000 hours, and a spoken archive of holocaust survivor testimonials called MALACH 176 hours. On Switchboard 300/2000 hours, we reach a single model performance of 8.9%/6.7% WER on the combined test set of the Hub5 2000 evaluation, respectively, and on MALACH we improve the WER by 7% relative over the previous best published result. In addition, we present empirical evidence suggesting that DSS layers learn damped Fourier basis functions where the attenuation coefficients are layer specific whereas the frequency coefficients converge to almost identical linearly-spaced values across all layers.

📄 PDF Abstract BibTeX arXiv:2302.14120

Code (0)

등록된 구현이 없습니다.

Tasks

speech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

On the Usefulness of Self-Attention for Automatic Speech Recognition with Transformers

2020-11-08 · Shucong Zhang, Erfan Loweimi, Peter Bell, Steve Renals

Self-attention models such as Transformers, which can capture temporal relationships without being limited by the distance between events, have given competitive speech recognition results. However, we note the range of …

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Diagonal State Spaces are as Effective as Structured State Spaces

2022-03-27 · Ankit Gupta, Albert Gu, Jonathan Berant

Modeling long range dependencies in sequential data is a fundamental step towards attaining human-level performance in many modalities such as text, vision, audio and video. While attention-based models are a popular and…

Long-range modeling

On Structured State-Space Duality

2025-10-06 · Jerry Yao-Chieh Hu, Xiwen Zhang, Ali ElSheikh, Weimin Wu 외 arxiv

Structured State-Space Duality (SSD) [Dao & Gu, ICML 2024] is an equivalence between a simple Structured State-Space Model (SSM) and a masked attention mechanism. In particular, a state-space model with a scalar-times-id…

On the Parameterization and Initialization of Diagonal State Space Models

2022-06-23 · Albert Gu, Ankit Gupta, Karan Goel, Christopher Ré

State space models (SSM) have recently been shown to be very effective as a deep learning layer as a promising alternative to sequence models such as RNNs, CNNs, or Transformers. The first version to show this potential …

Long-range modelingState Space ModelsTime Series Analysis

Enhanced Latent Multi-view Subspace Clustering

2023-12-22 · Long Shi, Lei Cao, Jun Wang, Badong Chen

Latent multi-view subspace clustering has been demonstrated to have desirable clustering performance. However, the original latent representation method vertically concatenates the data matrices from multiple views into …

ClusteringMulti-view Subspace Clustering