No article text was recorded for this version.
two-stage style and speaker adaptation
Version 1 of 128 papers31 conceptsfrozen 2026-10-04
Papers in this version
- Blog: The 2004 BBN 1xRT recognition systems for English broadcast news and conversational telephone speech
- Blog: Conversational spontaneous speech synthesis using average voice model
- Blog: Using unsupervised feature-based speaker adaptation for improved transcription of spoken archives
- Blog: MOPSA: Mixture of Prompt-Experts Based Speaker Adaptation for Elderly Speech Recognition
- Blog: Dynamic language model adaptation using keyword category classification
- Blog: The IRST English-Spanish translation system for european parliament speeches
- Blog: Transcribing lectures and seminars
- Blog: The BBN Byblos 2000 conversational Mandarin LVCSR system
- Blog: A comparative study of adaptive, automatic recognition of disordered speech
- Blog: A system for automatic broadcast news summarisation, geolocation and translation
- Blog: The 2014 KIT IWSLT speech-to-text systems for English, German and Italian
- Blog: Lombard Speech Synthesis Using Transfer Learning in a Tacotron Text-to-Speech System
- Blog: Advances in Mandarin broadcast speech recognition
- Blog: The 2000 BBN Byblos LVCSR system
- Blog: Adaptive training using discriminative mapping transforms
- Blog: Cross-Domain Adaptation with Discrepancy Minimization for Text-Independent Forensic Speaker Verification
- Blog: The BBN Mandarin broadcast news transcription system
- Blog: Discriminative Layered Nonnegative Matrix Factorization for Speech Separation
- Blog: Analysis of the characteristics of talk-show TV programs
- Blog: Unsupervised acoustic model adaptation for multi-origin non native ASR
- Blog: The USFD SLT system for IWSLT 2014
- Blog: Vocabulary and language model adaptation using information retrieval
- Blog: Speaker Adaptation and Adaptive Training for Jointly Optimised Tandem Systems
- Blog: Two-step unsupervised speaker adaptation based on speaker and gender recognition and HMM combination
- Blog: Spectral subtraction in likelihood-maximizing framework for robust speech recognition
- Blog: Towards speaker adaptive training of deep neural network acoustic models
- Blog: Maximum a posteriori eigenvoice speaker adaptation for Korean connected digit recognition
- Blog: Improving spoken document retrieval by unsupervised language model adaptation using utterance-based web search
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_two_stage_style_and_speaker_adaptation_b883be4d,
title = {two-stage style and speaker adaptation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/two-stage-style-and-speaker-adaptation/rdr_b883be4db9224307bd2f6cd0567bb3e4},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_two_stage_style_and_speaker_adaptation_b883be4d_v1,
title = {two-stage style and speaker adaptation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/two-stage-style-and-speaker-adaptation/rdr_b883be4db9224307bd2f6cd0567bb3e4/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}