Acoustic Feature Combination for Robust Speech Recognition

Zolnay, András; Schlüter, Ralf; Ney, Hermann

doi:10.1109/icassp.2005.1415149

Cited by 43 publications

(31 citation statements)

References 8 publications

(7 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, we present results on the integration of the tonal and the NN features with the MFCC features. In the literature, several ways to combine multiple feature streams are proposed [7,8,9]. We compare the approaches and motivate the integration method used for the final system.…”

Section: Introductionmentioning

confidence: 99%

Development of the 2007 RWTH Mandarin LVCSR system

Hoffmeister

Plahl

Fritz

et al. 2007

2007 IEEE Workshop on Automatic Speech Recognition &Amp; Understanding (ASRU)

View full text Add to dashboard Cite

This paper describes the development of the RWTH Mandarin LVCSR system. Different acoustic front-ends together with multiple system cross-adaptation are used in a two stage decoding framework. We describe the system in detail and present systematic recognition results. Especially, we compare a variety of approaches for cross-adapting to multiple systems.During the development we did a comparative study on different methods for integrating tone and phoneme posterior features. Furthermore, we apply lattice based consensus decoding and system combination methods. In these methods, the effect of minimizing character instead of word errors is compared. The final system obtains a character error rate of 17.7% on the GALE 2006 evaluation data.

show abstract

Section: Introductionmentioning

confidence: 99%

Development of the 2007 RWTH Mandarin LVCSR system

Hoffmeister

Plahl

Fritz

et al. 2007

2007 IEEE Workshop on Automatic Speech Recognition &Amp; Understanding (ASRU)

View full text Add to dashboard Cite

show abstract

“…In order to unify the emissions streams into the final emission model we use log-linear model combination as is customary in automatic speech recognition (e.g., [28]):…”

Section: Fig 4 Flexible Chord Onset (Fco)mentioning

confidence: 99%

Integrating Additional Chord Information Into HMM-Based Lyrics-to-Audio Alignment

Mauch

Fujihara

Goto

2012

IEEE Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Abstract-Aligning lyrics to audio has a wide range of applications such as the automatic generation of karaoke scores, song-browsing by lyrics, and the generation of audio thumbnails. Existing methods are restricted to using only lyrics and match them to phoneme features extracted from the audio (usually mel-frequency cepstral coefficients). Our novel idea is to integrate the textual chord information provided in the paired chords-lyrics format known from song books and Internet sites into the inference procedure. We propose two novel methods that implement this idea: First, assuming that all chords of a song are known, we extend a hidden Markov model (HMM) framework by including chord changes in the Markov chain and an additional audio feature (chroma) in the emission vector; second, for the more realistic case in which some chord information is missing, we present a method that recovers the missing chord information by exploiting repetition in the song. We conducted experiments with five changing parameters and show that with accuracies of 87.5% and 76.7%, respectively, both methods perform better than the baseline with statistical significance. We introduce the new accompaniment interface Song Prompter, which uses the automatically aligned lyrics to guide musicians through a song. It demonstrates that the automatic alignment is accurate enough to be used in a musical performance.Index Terms-Audio user interfaces, hidden Markov models (HMMs), music, music information retrieval, speech processing.

show abstract

“…In the past, numerous approaches to combine information from different feature streams and/or classification strategies have been proposed. Typically, one discerns fusion at the level of features [2,3,4,5], at the level of probabilities [6,7,8,9,10], and at the level of hypotheses [11,12,13,14].…”

Section: Introductionmentioning

confidence: 99%

Analytical Assessment of Dual-Stream Merging for Noise-Robust ASR

2016

View full text Add to dashboard Cite

In previous studies (on Aurora2), it was found that merging a posteriori probability streams from different classifiers (GMM, MLP, Sparse Coding) can improve the noise robustness of ASR. Maximizing word accuracy required the stream weights to be systematically dependent on the specific input streams and SNR. The tuning of the weights, however, was largely a matter of trial and error and typically involved a laborious grid search. In this paper, we propose two fundamental, analytical methods to better understand these empirical findings. To that end, we maximize the trustworthiness of merged streams as function of the stream weights. Trustworthiness is defined as the probability that the winning state in a probability vector correctly predicts a golden reference state obtained by a forced alignment. Even though our approach is not directly equivalent to optimizing word accuracy, both methods appear highly useful to obtain insight in stream properties that determine the success of a given merge (or the lack thereof). Furthermore, both methods clearly support the trends that exist in the grid-search based empirical observations.

show abstract

Acoustic Feature Combination for Robust Speech Recognition

Cited by 43 publications

References 8 publications

Development of the 2007 RWTH Mandarin LVCSR system

Development of the 2007 RWTH Mandarin LVCSR system

Integrating Additional Chord Information Into HMM-Based Lyrics-to-Audio Alignment

Analytical Assessment of Dual-Stream Merging for Noise-Robust ASR

Contact Info

Product

Resources

About