scispace - formally typeset
Proceedings ArticleDOI

Speech recognition using synchronization between speech and finger tapping.

Reads0
Chats0
TLDR
Leveraging the synchrony between speech and finger tapping provides a 46 % relative improvement and a 1 % absolute improvement in connected digit recognition experiments and LVCSR experiments, respectively.
Abstract
Behavioral synchronization between speech and finger tapping provides a novel approach to the improvement of speech recognition accuracy. We combine a sequence of finger tapping timings recorded alongside an utterance using two distinct methods: in the first method, HMM state transition probabilities at the word boundaries are controlled by the timing of the finger tapping; in the second, the probability (relative frequency) of the finger tapping is used as a ’feature’ and combined with MFCC in a HMM recognition system. We evaluate these methods through connected digit recognition under different noise conditions (AURORA-2J) and LVCSR tasks. Leveraging the synchrony between speech and finger tapping provides a 46 % relative improvement and a 1 % absolute improvement in connected digit recognition experiments and LVCSR experiments, respectively.

read more

Citations
More filters
Patent

Information processing method and electronic device

TL;DR: In this article, an information processing method and an electronic device are presented, where the electronic device generates M components to be embedded into a first application program when installing a recording application program, M is an integer greater than or equal to 1.
Journal ArticleDOI

Improvement of multimodal gesture and speech recognition performance using time intervals between gestures and accompanying speech

TL;DR: An integrative method of recognizing gestures such as pointing, accompanying speech using a probability distribution which expresses the distribution of the time interval between the starting times of gestures and of the corresponding utterances is proposed.
Journal ArticleDOI

Semi-synchronous speech and pen input for mobile user interfaces

TL;DR: A multi-modal recognition algorithm is developed that can handle this asynchronicity (time-lag) of speaking and writing by using a segment-based unification scheme and a method of adapting to the time-lag characteristics of individual users.
Patent

Processing method and electronic device for determining logic boundaries between speech information using information input in a different collection manner

Haisheng Dai, +1 more
TL;DR: In this paper, an information processing method and an electronic device are provided, where the electronic device is in a speech collection state for obtaining speech information through a first collection manner, and determining a logic boundary position in relation to a first speech information in accordance with the input information.
References
More filters
Proceedings Article

The aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions

TL;DR: A database designed to evaluate the performance of speech recognition algorithms in noisy conditions and recognition results are presented for the first standard DSR feature extraction scheme that is based on a cepstral analysis.
Journal ArticleDOI

Two coupled oscillators as a model for the coordinated finger tapping by both hands

TL;DR: The control mechanism of the coordinated finger tapping by both hands may be composed of a coupled system of two neural oscillators each of which controls the right and the left finger tapping respectively.
Proceedings Article

Data collection and evaluation of aurora-2 japanese corpus

TL;DR: A Japanese noisy speech corpus and its evaluation scripts, called AURORA-2J, which includes Japanese connected digits and command words collected in a moving car and its baseline performance is described.