Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

Lattice-Free MMI Adaptation Of Self-Supervised Pretrained Acoustic Models

Domaine:

natural language processing

Type de record:

papermodel
Créateur:
VyaMadBou
Hôte:avatar
In this work, we propose lattice-free MMI (LFMMI) for supervised adaptation of self-supervised pretrained acoustic model. We pretrain a Transformer model on thousand hours of untranscribed Librispeech data followed by supervised adaptation with LFMMI on three different datasets. Our results show that fine-tuning with LFMMI, we consistently obtain relative WER improvements of 10% and 35.3% on the clean and other test sets of Librispeech (100h), 10.8% on Switchboard (300h), and 4.3% on Swahili (38h) and 4.4% on Tagalog (84h) compared to the baseline trained only with supervised data.

Visit

arxiv.org

Tasks

automatic speech recognitionspeech processing

Languages

Swahili

Tags

Machine LearningSoundAudio and Speech Processing

Similaires

Pretrained self-supervised speech models can recognize unseen consonantsLattice-Based Unsupervised Test-Time Adaptation of Neural Network Acoustic ModelsAnalyzing Acoustic Word Embeddings from Pre-trained Self-supervised ModelsAnalyzing Acoustic Word Embeddings from Pre-trained Self-supervised Speech ModelsSelf-Supervised Acoustic Word Embedding Learning via Correspondence Transformer EncoderBenchmarking Self-Supervised Speech Models on Multilingual Nigerian Speech

Pretrained self-supervised speech models can recognize unseen consonants

Modern pretrained self-supervised automatic speech recognition models are trained on large-scale aud

Lattice-Based Unsupervised Test-Time Adaptation of Neural Network Acoustic Models

Acoustic model adaptation to unseen test recordings aims to reduce the mismatch between training and

Analyzing Acoustic Word Embeddings from Pre-trained Self-supervised Models

IEEE ICASSP 2023 Conference, Hybrid Event, 4-10 June 2023, Rhodes Island, Greece Given the strong re

Analyzing Acoustic Word Embeddings from Pre-trained Self-supervised Speech Models

Given the strong results of self-supervised models on various tasks, there have been surprisingly fe

Self-Supervised Acoustic Word Embedding Learning via Correspondence Transformer Encoder

Acoustic word embeddings (AWEs) aims to map a variable-length speech segment into a fixed-dimensiona

Benchmarking Self-Supervised Speech Models on Multilingual Nigerian Speech

Self-supervised speech models such as Whisper and wav2vec 2.0 have significantly advanced automatic