A linear memory CTC-based algorithm for text-to-voice alignment of very long audio recordings
Synchronisation of a voice recording with the corresponding text is a common task in speech
and music processing, and is used in many practical applications (automatic subtitling …
and music processing, and is used in many practical applications (automatic subtitling …
Probabilistic kernels for improved text-to-speech alignment in long audio tracks
G Bordel, M Penagarikano… - IEEE Signal …, 2015 - ieeexplore.ieee.org
The synchronization of text transcripts with audio tracks is typically solved by forced
alignment at the phonetic level. However, when dealing with either very long audio tracks or …
alignment at the phonetic level. However, when dealing with either very long audio tracks or …
The development of the Cambridge University alignment systems for the Multi-Genre Broadcast challenge
We describe the alignment systems developed both for the preparation of data for the Multi-
Genre Broadcast (MGB) challenge and for our participation in the transcription and …
Genre Broadcast (MGB) challenge and for our participation in the transcription and …
Finger tracking: facilitating non-commercial content production for mobile e-reading applications
Limited literacy and visual impairment reduce the ability of many to read on their own.
Current e-reader solutions rely on either unnatural synthetic voices or professionally …
Current e-reader solutions rely on either unnatural synthetic voices or professionally …
[PDF][PDF] Enhancing Data-Driven Phone Confusions Using Restricted Recognition.
M Kane, J Carson-Berndsen - INTERSPEECH, 2016 - isca-archive.org
This paper presents a novel approach to address data sparseness in standard confusion
matrices and demonstrates how enhanced matrices, which capture additional similarities …
matrices and demonstrates how enhanced matrices, which capture additional similarities …
Improving a long audio aligner through phone-relatedness matrices for english, spanish and basque
A multilingual long audio alignment system is presented in the automatic subtitling domain,
supporting English, Spanish and Basque. Pre-recorded contents are recognized at …
supporting English, Spanish and Basque. Pre-recorded contents are recognized at …
Automatic alignment of phonetic transcriptions for russian
D Kocharov - Speech and Computer: 16th International Conference …, 2014 - Springer
This paper presents automatic alignment of Russian phonetic pronunciations using the
information about phonetic nature of speech sounds in the aligned transcription sequences …
information about phonetic nature of speech sounds in the aligned transcription sequences …
Speech technologies for the audiovisual and multimedia interaction environments
A Álvarez Muniain - 2016 - portalcientifico.uvigo.gal
En esta memoria de tesis, se analiza el estado actual de algunas tecnologías de análisis del
audio y procesamiento del habla aplicadas a sectores como el audiovisual y el de …
audio y procesamiento del habla aplicadas a sectores como el audiovisual y el de …
Phoneme alignment using the information on phonological processes in continuous speech
D Kocharov - Proceedings of the Tenth International Conference …, 2016 - aclanthology.org
The current study focuses on optimization of Levenshtein algorithm for the purpose of
computing the optimal alignment between two phoneme transcriptions of spoken utterance …
computing the optimal alignment between two phoneme transcriptions of spoken utterance …
On automatic cross-lingual subtitle timing
M Bohac, M Rott, K Blavka - 2015 IEEE International Workshop …, 2015 - ieeexplore.ieee.org
In the last years automatic speech recognition (ASR) technologies are applied as assistant
technologies for hearing-impaired people. ASR technologies typically produce some kind of …
technologies for hearing-impaired people. ASR technologies typically produce some kind of …