Jasha Droppo

Jasha Droppo

Auto-generated profile, based on publicly available information

Jasha Droppo

Microsoft AI and Research, Redmond, WA, USA

Research Focus & Metrics

Academic Career Length

25Years (2002-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 April 2018
Verified
Conference Paper
Closed access
WXW. Xiong
W. Xiong
LWL. Wu
L. Wu
FAF. Alleva
F. Alleva
JDJ. Droppo
J. Droppo
XHX. Huang
X. Huang
ASA. Stolcke
A. Stolcke
We describe the latest version of Microsoft's conversational speech recognition system for the Switchboard and CallHome domains. The system adds a CNN-BLSTM acoustic model to the set of model architectures we combined previously, and includes character-based and dialog session aware LSTM language models in rescoring. For system combination we adopt a two-stage approach, whereby acoustic model posteriors are first combined at the senone/frame level, followed by a word-level voting via confusion networks. We also added another language model rescoring step following the confusion network combination. The resulting system yields a 5.1% word error rate on the NIST 2000 Switchboard test set, and 9.8% on the CallHome subset.

26 September 2017 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
WXWayne Xiong
Wayne Xiong
JDJasha Droppo
Jasha Droppo
XHXuedong Huang
Xuedong Huang
FSFrank Seide
Frank Seide
MSMichael L. Seltzer
Michael L. Seltzer
GZGeoffrey Zweig
Geoffrey Zweig
Conversational speech recognition has served as a flagship speech recognition task since the release of the Switchboard corpus in the 1990s. In this paper, we measure a human error rate on the widely used NIST 2000 test set for commercial bulk transcription. The error rate of professional transcribers is 5.9% for the Switchboard portion of the data, in which newly acquainted pairs of people discuss an assigned topic, and 11.3% for the CallHome portion, where friends and family members have open-ended conversations. In both cases, our automated system edges past the human benchmark, achieving error rates of 5.8% and 11.0%, respectively. The key to our system's performance is the use of various convolutional and long-short-term memory acoustic model architectures, combined with a novel spatial smoothing method and lattice-free discriminative acoustic training, multiple recurrent neural network language modeling approaches, and a systematic use of system combination. Comparing frequent errors in our human and machine transcripts, we find them to be remarkably similar, and highly correlated as a function of the speaker. Human subjects find it very difficult to tell which errorful transcriptions come from humans. Overall, this suggests that, given sufficient matched training data, conversational speech transcription engines are approximating human parity in both quantitative and qualitative terms.

1 March 2017
Verified
Conference Paper
Closed access
WXW. Xiong
W. Xiong
JDJ. Droppo
J. Droppo
XHX. Huang
X. Huang
FSF. Seide
F. Seide
MSM. Seltzer
M. Seltzer
GZG. Zweig
G. Zweig
We describe Microsoft's conversational speech recognition system, in which we combine recent developments in neural-network-based acoustic and language modeling to advance the state of the art on the Switchboard recognition task. Inspired by machine learning ensemble techniques, the system uses a range of convolutional and recurrent neural networks. I-vector modeling and lattice-free MMI training provide significant gains for all acoustic model architectures. Language model rescoring with multiple forward and backward running RNNLMs, and word posterior-based system combination provide a 20% boost. The best single system uses a ResNet architecture acoustic model with RNNLM rescoring, and achieves a word error rate of 6.9% on the NIST 2000 Switchboard task. The combined system has an error rate of 6.2%, representing an improvement over previously reported results on this benchmark task.

1 May 2013
Verified
Conference Paper
Closed access
MSMichael L. Seltzer
Michael L. Seltzer
JDJasha Droppo
Jasha Droppo
In this paper we demonstrate how to improve the performance of deep neural network (DNN) acoustic models using multi-task learning. In multi-task learning, the network is trained to perform both the primary classification task and one or more secondary tasks using a shared representation. The additional model parameters associated with the secondary tasks represent a very small increase in the number of trained parameters, and can be discarded at runtime. In this paper, we explore three natural choices for the secondary task: the phone label, the phone context, and the state context. We demonstrate that, even on a strong baseline, multi-task learning can provide a significant decrease in error rate. Using phone context, the phonetic error rate (PER) on TIMIT is reduced from 21.63% to 20.25% on the core test set, and surpassing the best performance in the literature for a DNN that uses a standard feed-forward network architecture.

11 June 2015 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
CWChao Weng
Chao Weng
DYDong Yu
Dong Yu
MSMichael L. Seltzer
Michael L. Seltzer
JDJasha Droppo
Jasha Droppo
We investigate techniques based on deep neural networks (DNNs) for attacking the single-channel multi-talker speech recognition problem. Our proposed approach contains five key ingredients: a multi-style training strategy on artificially mixed speech data, a separate DNN to estimate senone posterior probabilities of the louder and softer speakers at each frame, a weighted finite-state transducer (WFST)-based two-talker decoder to jointly estimate and correlate the speaker and speech, a speaker switching penalty estimated from the energy pattern change in the mixed-speech, and a confidence based system combination strategy. Experiments on the 2006 speech separation and recognition challenge task demonstrate that our proposed DNN-based system has remarkable noise robustness to the interference of a competing speaker. The best setup of our proposed systems achieves an average word error rate (WER) of 18.8% across different SNRs and outperforms the state-of-the-art IBM superhuman system by 2.8% absolute with fewer assumptions.

18 April 2005 in IEEE Transactions on Speech and Audio Processing
Verified
Journal Article
Closed access
LDLi Deng
Li Deng
JDJ. Droppo
J. Droppo
AAA. Acero
A. Acero
This paper presents a new technique for dynamic, frame-by-frame compensation of the Gaussian variances in the hidden Markov model (HMM), exploiting the feature variance or uncertainty estimated during the speech feature enhancement process, to improve noise-robust speech recognition. The new technique provides an alternative to the Bayesian predictive classification decision rule by carrying out an integration over the feature space instead of over the model-parameter space, offering a much simpler system implementation, lower computational cost, and dynamic compensation capabilities at the frame level. The computation of the feature enhancement variances is carried out using a probabilistic and parametric model of speech distortion, free from the use of any stereo training data. Dynamic compensation of the Gaussian variances in the HMM recognizer is derived, which is simply enlarging the HMM Gaussian variances by the feature enhancement variances. Experimental evaluation using the full Aurora2 test data sets demonstrates a significant digit error rate reduction, averaged over all noisy and signal-to-noise-ratio conditions, compared with the baseline that did not exploit the enhancement variance information. When the true enhancement variances are used, further dramatic error rate reduction is observed, indicating the strong potential for the new technique and the strong need for high accuracy in estimating the variances associated with feature enhancement. All the results, using either the true variances of the enhanced features or the estimated ones, show that the greatest contribution to recognizer's performance improvement is due to the use of the uncertainty for the static features, next due to the delta features, and the least due to the delta-delta features.