paper-with-me

홈 › Papers

An Exploration of Length Generalization in Transformer-Based Speech Enhancement

2024-06-17 · Qiquan Zhang, Hongxu Zhu, Xinyuan Qian, Eliathamby Ambikairajah, Haizhou Li

The use of Transformer architectures has facilitated remarkable progress in speech enhancement. Training Transformers using substantially long speech utterances is often infeasible as self-attention suffers from quadratic complexity. It is a critical and unexplored challenge for a Transformer-based speech enhancement model to learn from short speech utterances and generalize to longer ones. In this paper, we conduct comprehensive experiments to explore the length generalization problem in speech enhancement with Transformer. Our findings first establish that position embedding provides an effective instrument to alleviate the impact of utterance length on Transformer-based speech enhancement. Specifically, we explore four different position embedding schemes to enable length generalization. The results confirm the superiority of relative position embeddings (RPEs) over absolute PE (APEs) in length generalization.

📄 PDF Abstract BibTeX arXiv:2406.11401

Code (0)

등록된 구현이 없습니다.

Tasks

PositionSpeech Enhancement

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Residual Connection 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

Exploring Length Generalization For Transformer-based Speech Enhancement

2025-06-07 · Qiquan Zhang, Hongxu Zhu, Xinyuan Qian, Eliathamby Ambikairajah 외

Transformer network architecture has proven effective in speech enhancement. However, as its core module, self-attention suffers from quadratic complexity, making it infeasible for training on long speech utterances. In …

Speech Enhancement

DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors

2024-06-17 · Keon Lee, Dong Won Kim, Jaehyeon Kim, Seungjun Chung 외

Large-scale latent diffusion models (LDMs) excel in content generation across various modalities, but their reliance on phonemes and durations in text-to-speech (TTS) limits scalability and access from other fields. Whil…

text-to-speechText to Speech

Robust and Unbounded Length Generalization in Autoregressive Transformer-Based Text-to-Speech

2024-10-29 · Eric Battenberg, RJ Skerry-Ryan, Daisy Stanton, Soroosh Mariooryad 외

Autoregressive (AR) Transformer-based sequence models are known to have difficulty generalizing to sequences longer than those seen during training. When applied to text-to-speech (TTS), these models tend to drop or repe…

Decodertext-to-speechText to Speech

DPATD: Dual-Phase Audio Transformer for Denoising

2023-10-30 · Junhui Li, Pu Wang, Jialu Li, Xinzhe Wang 외

Recent high-performance transformer-based speech enhancement models demonstrate that time domain methods could achieve similar performance as time-frequency domain methods. However, time-domain speech enhancement systems…

DenoisingSpeech Enhancement

Selective State Space Model for Monaural Speech Enhancement

2024-11-09 · Moran Chen, Qiquan Zhang, Mingjiang Wang, Xiangyu Zhang 외

Voice user interfaces (VUIs) have facilitated the efficient interactions between humans and machines through spoken commands. Since real-word acoustic scenes are complex, speech enhancement plays a critical role for robu…

MambaSpeech Enhancement