The 2015 sheffield system for transcription of Multi-Genre Broadcast media

Saz, Óscar; Doulaty, Mortaza; Deena, Salil; Milner, Rosanna; Ng, Raymond W. M.; Hasan, Madina; Liu, Yulan; Hain, Thomas

doi:10.1109/asru.2015.7404854

Cited by 19 publications

(21 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• University of Sheffield (SU; spandh.dcs.shef.ac.uk) [26]: 1st pass -DNNs with PLP+bMMI features with global cMLLR xform. Speech segmented based on 1st-pass output.…”

Section: Submitted Systems and Resultsmentioning

confidence: 99%

The MGB challenge: Evaluating multi-genre broadcast media recognition

Bell

Gales

Hain

et al. 2015

2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)

125

151

View full text Add to dashboard Cite

This paper describes the Multi-Genre Broadcast (MGB) Challenge at ASRU 2015, an evaluation focused on speech recognition, speaker diarization, and "lightly supervised" alignment of BBC TV recordings. The challenge training data covered the whole range of seven weeks BBC TV output across four channels, resulting in about 1,600 hours of broadcast audio. In addition several hundred million words of BBC subtitle text was provided for language modelling. A novel aspect of the evaluation was the exploration of speech recognition and speaker diarization in a longitudinal setting -i.e. recognition of several episodes of the same show, and speaker diarization across these episodes, linking speakers. The longitudinal tasks also offered the opportunity for systems to make use of supplied metadata including show title, genre tag, and date/time of transmission. This paper describes the task data and evaluation process used in the MGB challenge, and summarises the results obtained.

show abstract

“…• University of Sheffield (SU; spandh.dcs.shef.ac.uk) [26]: 1st pass -DNNs with PLP+bMMI features with global cMLLR xform. Speech segmented based on 1st-pass output.…”

Section: Submitted Systems and Resultsmentioning

confidence: 99%

The MGB challenge: Evaluating multi-genre broadcast media recognition

Bell

Gales

Hain

et al. 2015

2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)

125

151

View full text Add to dashboard Cite

show abstract

“…The setup for ASR experiments is the same as in [23,6] with a baseline 4-gram language model built on LM 1+LM 2 text by first selecting a vocabulary of 200k words was chosen from all the words in the LM 2 text (87k) and augmented with the most frequently occuring words in LM 1. The RNNLMs were trained with a 60k vocabulary for the input word list and a 50k vocabulary for the output word list, both obtained by shortlisting the 200k vocabulary based on most frequent words.…”

Section: Methodsmentioning

confidence: 99%

Semi-Supervised Adaptation of RNNLMs by Fine-Tuning with Domain-Specific Auxiliary Features

Deena

Madhyastha

et al. 2017

Interspeech 2017

Self Cite

View full text Add to dashboard Cite

Recurrent neural network language models (RNNLMs) can be augmented with auxiliary features, which can provide an extra modality on top of the words. It has been found that RNNLMs perform best when trained on a large corpus of generic text and then fine-tuned on text corresponding to the sub-domain for which it is to be applied. However, in many cases the auxiliary features are available for the sub-domain text but not for the generic text. In such cases, semi-supervised techniques can be used to infer such features for the generic text data such that the RNNLM can be trained and then fine-tuned on the available in-domain data with corresponding auxiliary features.In this paper, several novel approaches are investigated for dealing with the semi-supervised adaptation of RNNLMs with auxiliary features as input. These approaches include: using zero features during training to mask the weights of the feature sub-network; adding the feature sub-network only at the time of fine-tuning; deriving the features using a parametric model and; back-propagating to infer the features on the generic text. These approaches are investigated and results are reported both in terms of PPL and WER on a multi-genre broadcast ASR task.

show abstract

“…The MGB data is a large broad and multigenre, spanning the whole range of TV output. The Automatic transcriptions were produced by the Sheffield system described in [3]. This system was built using two different types of systems.…”

Section: Experimental Setup 41 Data and Asr Systemmentioning

confidence: 99%

“…The focus of this work was on substitution and insertion errors. The proposed system was evaluated on the transcription of a dataset from Multi-Genre Broadcast Media using Sheffield ASR system [3].…”

Section: Introductionmentioning

confidence: 99%

Automatic speech recognition errors detection using supervised learning techniques

Errattahi

Ouahmane

Hain

2016

2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA)

Self Cite

View full text Add to dashboard Cite

Abstract-Over the last years, many advances have been made in the field of Automatic Speech Recognition (ASR). However, the persistent presence of ASR errors is limiting the widespread adoption of speech technology in real life applications. This motivates the attempts to find alternative techniques to automatically detect and correct ASR errors, which can be very effective and especially when the user does not have access to tune the features, the models or the decoder of the ASR system or when the transcription serves as input to downstream systems like machine translation, information retrieval, and question answering. In this paper, we present an ASR errors detection system targeted towards substitution and insertion errors. The proposed system is based on supervised learning techniques and uses input features deducted only from the ASR output words and hence should be usable with any ASR system. Applying this system on TV program transcription data leads to identify 40.30% of the recognition errors generated by the ASR system.

show abstract

The 2015 sheffield system for transcription of Multi-Genre Broadcast media

Cited by 19 publications

References 26 publications

The MGB challenge: Evaluating multi-genre broadcast media recognition

The MGB challenge: Evaluating multi-genre broadcast media recognition

Semi-Supervised Adaptation of RNNLMs by Fine-Tuning with Domain-Specific Auxiliary Features

Automatic speech recognition errors detection using supervised learning techniques

Contact Info

Product

Resources

About