Speech recognition decoders based on static graphs have recently proven to significantly outperform the traditional approach of prefix tree expansion in terms of decoding speed. The reduced search effort makes static graph decoders an attractive alternative for tasks concerned with limited processing power or memory footprint on devices such as PDAs, internet tablets, and smart phones. In this paper we explore the benefits of decoding with an optimized speech recognition network over the fully task-optimized prefix-tree based decoder IBIS. We designed and implemented a new decoder called SWIFT (speedy weigthed finite-state transducer) based on WFSTs with its application to embedded platforms in mind. After describing the design, the network construction and storage process, we present evaluation results on a small task suitable for embedded applications, and on a large task, namely the European Parliament Plenary Sessions (EPPS) task from the TC-STAR project. The SWIFT Decoder is up to 50% faster than IBIS on both tasks. In addition, SWIFT achieves significant memory consumption reductions obtained by our innovative network specific storage layout optimization.

In this work, we address an acoustic beamforming application where two speakers are simultaneously active. We construct one subband domain beamformer in generalized sidelobe canceller (GSC) configuration for each source. In contrast to normal practice, we then jointly adjust the active weight vectors of both GSCs to obtain two output signals with minimum mutual information (MMI). In order to calculate the mutual information of the complex subband snapshots, we consider four probability density functions (pdfs), namely the Gaussian, Laplace, K0and Г pdfs. The latter three belong to the class of super-Gaussian density functions that are typically used in independent component analysis as opposed to conventional beamforming. We demonstrate the effectiveness of our proposed technique through a series of far-field automatic speech recognition experiments on data from the PASCAL Speech Separation Challenge. In the experiments, the delay-and-sum beamformer achieved a word error rate (WER) of 70.4 %. The MMI beamformer under a Gaussian assumption achieved 55.2 % WER which was further reduced to 52.0 % with a K0pdf, whereas the WER for data recorded with close-talking microphone was 21.6 %.

In automatic speech recognition based on weighted-finite transducers, a static decoding graph HC o L o G is typically constructed. In this work, we first show how the size of the decoding graph can be reduced and the necessity of determinizing it can be eliminated by removing the ambiguity associated with transitions to the backoff state or states in G. We then show how the static construction can be avoided entirely by performing fast on-the-fly composition of HC and L o G. We demonstrate that speech recognition based on this on-the-fly composition approximately 80% more run-time than recognition based on the statically-expanded network R, which makes it competitive compared with other dynamic expansion algorithms that have appeared in the literature. Moreover, the dynamic algorithm requires a factor of approximately seven less main memory as the recognition based on the static decoding graph.

In earlier work, we derived a transducer HC that translates from sequences of Gaussian mixture models directly to phone sequences. The HC transducer was statically expanded then determinized and minimized. In this work, we present a refinement of the previous algorithm whereby the initial HC transducer is incrementally expanded and immediately determinized. This technique avoids the need for a full expansion of the initial HC, and thereby reduces the random access memory required to produce the determinized HC by a factor of more than five. With the incremental algorithm, we were able to construct HC for a semi-continuous acoustic model with 16,000 distributions which reduced the word error rate from 34.1% to 32.9% with respect to a fully-continuous system with 4,000 distributions on the lecture meeting portion of the NIST RT05 data.

In this paper, we consider an acoustic beamforming application where two speakers are simultaneously active. We construct one subband-domain beamformer in generalized sidelobe canceller (GSC) configuration for each source. In contrast to normal practice, we then jointly optimize the active weight vectors of both GSCs to obtain two output signals with minimum mutual information (MMI). Assuming that the subband snapshots are Gaussian-distributed, this MMI criterion reduces to the requirement that the cross-correlation coefficient of the subband outputs of the two GSCs vanishes. We also compare separation performance under the Gaussian assumption with that obtained from several super-Gaussian probability density functions (pdfs), namely, the Laplace$K_0$and$\Gamma$pdfs. Our proposed technique provides effective nulling of the undesired source, but without the signal cancellation problems seen in conventional beamforming. Moreover, our technique does not suffer from the source permutation and scaling ambiguities encountered in conventional blind source separation algorithms. We demonstrate the effectiveness of our proposed technique through a series of far-field automatic speech recognition experiments on data from the PASCAL Speech Separation Challenge (SSC). On the SSC development data, the simple delay-and-sum beamformer achieves a word error rate (WER) of 70.4%. The MMI beamformer under a Gaussian assumption achieves a 55.2% WER, which is further reduced to 52.0% with a$K_0$pdf, whereas the WER for data recorded with a close-talking microphone is 21.6%.

As coarticulation effects are prevalent in all speech, a phone must be modeled in its context to achieve optimal performance in large vocabulary continuous speech recognition systems. Schuster and Hori (2005) proposed a technique for modeling polyphone context with weighted finite-state transducers whereby all valid three-state sequences of Gaussian mixture models are enumerated, and there-after the possible connections between these three-state sequences are determined. Hence, the explicit modeling of all possible polyphones is avoided. Rather, Schuster and Hori derive a transducer HC that translates from sequences of Gaussian mixture models directly to phone sequences. The resulting network HC o L o G is much smaller than the conventional network H o C o L o G proposed by Mohri et al (1998). While Schuster and Hori's approach to modeling polyphone context is quite interesting, it is incorrect for contexts larger than triphones. In this work, we correct the errors of Schuster and Hori. Thereafter we discuss how the intermediate size of the network HC can be held in check. We also present the results of a set of experiments comparing network size and speech recognition performance for networks obtained with Schuster and Hori's technique and with the correct technique