paper-with-me

Papers

Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition System

2018-04-14 · Weicheng Cai, Jinkun Chen, Ming Li

In this paper, we explore the encoding/pooling layer and loss function in the end-to-end speaker and language recognition system. First, a unified and interpretable end-to-end system for both speaker and language recognition is developed. It accepts variable-length input and produces an utterance level result. In the end-to-end system, the encoding layer plays a role in aggregating the variable-length input sequence into an utterance level representation. Besides the basic temporal average pooling, we introduce a self-attentive pooling layer and a learnable dictionary encoding layer to get the utterance level representation. In terms of loss function for open-set speaker verification, to get more discriminative speaker embedding, center loss and angular softmax loss is introduced in the end-to-end system. Experimental results on Voxceleb and NIST LRE 07 datasets show that the performance of end-to-end learning system could be significantly improved by the proposed encoding layer and loss function.

📄 PDF Abstract BibTeX arXiv:1804.05160

Code (1)

jkchen79/netvlad-in-speech pytorch

Tasks

Speaker Verification

Methods 이 논문이 사용한 방법론

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 $x$…

Similar Papers 제목 키워드 기반

Spatial Pyramid Encoding with Convex Length Normalization for Text-Independent Speaker Verification

2019-06-19 · Youngmoon Jung, Younggwan Kim, Hyungjun Lim, Yeunju Choi 외

In this paper, we propose a new pooling method called spatial pyramid encoding (SPE) to generate speaker embeddings for text-independent speaker verification. We first partition the output feature maps from a deep residu…

Speaker VerificationText-Independent Speaker Verification

MCSAE: Masked Cross Self-Attentive Encoding for Speaker Embedding

2020-01-28 · Soonshin Seo, Ji-Hwan Kim

In general, a self-attention mechanism has been applied for speaker embedding encoding. Previous studies focused on training the self-attention in a high-level layer, such as the last pooling layer. However, the effect o…

Speaker Verification

Probing Speaker-specific Features in Speaker Representations

2025-01-09 · Aemon Yat Fei Chiu, Paco Kei Ching Fung, Roger Tsz Yeung Li, Jingyu Li 외

This study explores speaker-specific features encoded in speaker embeddings and intermediate layers of speech self-supervised learning (SSL) models. By utilising a probing method, we analyse features such as pitch, tempo…

Self-Supervised LearningSpeaker VerificationSpeech Synthesistext-to-speech+2

Serialized Speech Information Guidance with Overlapped Encoding Separation for Multi-Speaker Automatic Speech Recognition

2024-09-01 · Hao Shi, Yuan Gao, Zhaoheng Ni, Tatsuya Kawahara

Serialized output training (SOT) attracts increasing attention due to its convenience and flexibility for multi-speaker automatic speech recognition (ASR). However, it is not easy to train with attention loss only. In th…

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

Exploring Binary Classification Loss For Speaker Verification

2023-07-17 · Bing Han, Zhengyang Chen, Yanmin Qian

The mismatch between close-set training and open-set testing usually leads to significant performance degradation for speaker verification task. For existing loss functions, metric learning-based objectives depend strong…

Binary ClassificationClassificationMetric LearningSpeaker Verification