Automatic speech recognition and speech variability: A review
Major progress is being recorded regularly on both the technology and exploitation of
automatic speech recognition (ASR) and spoken language systems. However, there are still …
automatic speech recognition (ASR) and spoken language systems. However, there are still …
Query expansion with locally-trained word embeddings
F Diaz, B Mitra, N Craswell - ar** a system for automatically
transcribing and indexing audio-visual academic lectures for audio information retrieval. We …
transcribing and indexing audio-visual academic lectures for audio information retrieval. We …
[PDF][PDF] Style & topic language model adaptation using HMM-LDA
BJP Hsu, J Glass - Proceedings of the 2006 Conference on …, 2006 - aclanthology.org
Adapting language models across styles and topics, such as for lecture transcription,
involves combining generic style models with topic-specific content relevant to the target …
involves combining generic style models with topic-specific content relevant to the target …
Do smart speaker skills support diverse audiences?
Smart speakers with voice assistants like Google Home or Amazon Alexa are increasingly
popular and essential in our daily lives due to their convenience of issuing voice commands …
popular and essential in our daily lives due to their convenience of issuing voice commands …
Automatic lecture transcription by exploiting presentation slide information for language model adaptation
T Kawahara, Y Nemoto, Y Akita - 2008 IEEE International …, 2008 - ieeexplore.ieee.org
The paper addresses language model adaptation for automatic lecture transcription by fully
exploiting presentation slide information used in the lecture. As the text in the presentation …
exploiting presentation slide information used in the lecture. As the text in the presentation …
Exploiting automatic speech recognition errors to enhance partial and synchronized caption for facilitating second language listening
This paper addresses the viability of using Automatic Speech Recognition (ASR) errors as
the predictor of difficulties in speech segments, thereby exploiting them to improve Partial …
the predictor of difficulties in speech segments, thereby exploiting them to improve Partial …
A new ASR evaluation measure and minimum Bayes-risk decoding for open-domain speech understanding
H Nanjo, T Kawahara - Proceedings.(ICASSP'05). IEEE …, 2005 - ieeexplore.ieee.org
A new evaluation measure of speech recognition and a decoding strategy for keyword-
based open-domain speech understanding are presented. Conventionally, WER (word error …
based open-domain speech understanding are presented. Conventionally, WER (word error …
Modeling of speaking rate influences on Mandarin speech prosody and its application to speaking rate-controlled TTS
A new data-driven approach to building a speaking rate-dependent hierarchical prosodic
model (SR-HPM), directly from a large prosody-unlabeled speech database containing …
model (SR-HPM), directly from a large prosody-unlabeled speech database containing …