Efficient scalable encoding for distributed speech recognition

Srinivasamurthy, Naveen; Ortega, Antonio; Narayanan, Shrikanth

doi:10.1016/j.specom.2005.11.003

Cited by 17 publications

(10 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…What is more exciting is the possibility of distributing the processing work between a low resource client and a server machine without any change in implementation, leveraging the network transparency provided by libcppa. For instance, a smartphone can run early stages of the recognition pipeline, such as audio acquisition and feature extraction, while a remote server does the processor-intensive decoding [6]. …”

Section: Introductionmentioning

confidence: 99%

Barista: A framework for concurrent speech processing by usc-sail

Can

Gibson

Vaz

et al. 2014

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

We present Barista, an open-source framework for concurrent speech processing based on the Kaldi speech recognition toolkit and the libcppa actor library. With Barista, we aim to provide an easy-to-use, extensible framework for constructing highly customizable concurrent (and/or distributed) networks for a variety of speech processing tasks. Each Barista network specifies a flow of data between simple actors, concurrent entities communicating by message passing, modeled after Kaldi tools. Leveraging the fast and reliable concurrency and distribution mechanisms provided by libcppa, Barista lets demanding speech processing tasks, such as real-time speech recognizers and complex training workflows, to be scheduled and executed on parallel (and/or distributed) hardware. Barista is released under the Apache License v2.0.

show abstract

Section: Introductionmentioning

confidence: 99%

Barista: A framework for concurrent speech processing by usc-sail

Can

Gibson

Vaz

et al. 2014

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…The resulting source encoding bit-rate is 4.4 kbps. The authors in [5] present a scalable predictive approach, in which each feature is independently quantized using a uniform scalar quantizer, providing flexibility in optimizing the DSR system to the changing bandwidth requirement and server load, while achieving the best possible recognition performance. However, the performance is considerably reduced using the state of the art speech codec's at low bit-rate condition.…”

Section: Introductionmentioning

confidence: 99%

“…Bits allocation of the proposed encoder. 5 9 9 v 6 , v 7 , v 8 9 9 v 9 , v 10 , v 11 9 9 v 12 9 9 v 13 9 9…”

mentioning

confidence: 99%

A polynomial interpolation-based scheme for reducing bandwidth in distributed speech recognition system

Touazi

Debyeche

2013

2013 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics

View full text Add to dashboard Cite

In this paper, we propose a low bit-rate compression scheme in distributed speech recognition (DSR) system based on polynomial interpolation. Dimensionality reduction of a set of successive Mel frequency cepstral coefficients (MFCCs) is achieved by performing polynomial least squares fitting. A conventional vector quantization (VQ) is applied to the polynomial coefficients to achieve more than 58% of bandwidth reduction as compared to ETSI advanced front-end (ETSI-AFE) encoder. Evaluation performance has been conducted on the Aurora-2 database in clean and multi-condition training modes. With respect to ETSI-AFE, the results obtained with the proposed encoder show no significant degradation in term of overall recognition accuracy.

show abstract

“…These portable devices are typically small in size and difficult to manipulate, thus current IUIs available for them are limited. Thus, as a promising user interface to make them easier to use, speech recognition can take the place of the keyboard or touch pad on these devices since voice input only requires a microphone (Srinivasamurthy et al, 2006). A major problem, however, is that the computational complexity of speech recognition is too high for most portable devices.…”

Section: Introductionmentioning

confidence: 99%

“…Several coding methods for compressing MFCCs have been proposed in literature (Srinivasamurthy et al, 2006;Kiss, 2000;Zhu and Alwan, 2001;Hirsch, 1998;So and Paliwal, 2006;Borgstrom and Alwan, 2007;Digalakis et al, 1999;Ramaswamy and Gopalakrishnan, 1998;Kiss and Kapanen, 1999). In early attempts at compression, scalar quantization and vector quantization were applied to MFCCs, and the word error rates (WERs) were measured according to various bit-rates (Digalakis et al, 1999).…”

Section: Introductionmentioning

confidence: 99%