Hynek Hermansky

Hynek Hermansky

Auto-generated profile, based on publicly available information

Hynek Hermansky

Center for Language and Speech Processing Johns Hopkins University USA

Research Focus & Metrics

Academic Career Length

30Years (1997-Present)

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

Representative Publications

View All Publications
1 March 2012
Verified
Conference Paper
Closed access
STSamuel Thomas
Samuel Thomas
SGSriram Ganapathy
Sriram Ganapathy
HHHynek Hermansky
Hynek Hermansky
We introduce a new approach to training multilayer perceptrons (MLPs) for large vocabulary continuous speech recognition (LVCSR) in new languages which have only few hours of annotated in-domain training data (for example, 1 hour of data). In our approach, large amounts of annotated out-of-domain data from multiple languages are used to train multilingual MLP systems without dealing with the different phoneme sets for these languages. Features extracted from these MLP systems are used to train LVCSR systems in the low-resource language similar to the Tandem approach. In our experiments, the proposed features provide a relative improvement of about 30% in an low-resource LVCSR setting with only one hour of training data.

1 May 2013
Verified
Conference Paper
Closed access
AJAren Jansen
Aren Jansen
STSamuel Thomas
Samuel Thomas
HHHynek Hermansky
Hynek Hermansky
Typical supervised acoustic model training relies on strong top-down constraints provided by dynamic programming alignment of the input observations to phonetic sequences derived from orthographic word transcripts and pronunciation dictionaries. This paper investigates a much weaker form of top-down supervision for use in place of transcripts and dictionaries in the zero resource setting. Our proposed constraints, which can be produced using recent spoken term discovery systems, come in the form of pairs of isolated word examples that share the same unknown type. For each pair, we perform a dynamic programming alignment of the acoustic observations of the two constituent examples, generating an inventory of cross-speaker frame pairs that each provide evidence that the same subword unit model should account for them. We find these weak top-down constraints are capable of improving model speaker independence by up to 57% relative over bottom-up training alone.

1 October 2011 in Sādhanā
Verified
Journal Article
Closed access
PDF file
HHHynek Hermansky
Hynek Hermansky

1 December 2010 in The Journal of the Acoustical Society of America
Verified
Journal Article
Closed access
SGSriram Ganapathy
Sriram Ganapathy
STSamuel Thomas
Samuel Thomas
HHHynek Hermansky
Hynek Hermansky
A robust feature extraction technique for phoneme recognition is proposed which is based on deriving modulation frequency components from the speech signal. The modulation frequency components are computed from syllable-length segments of sub-band temporal envelopes estimated using frequency domain linear prediction. Although the baseline features provide good performance in clean conditions, the performance degrades significantly in noisy conditions. In this paper, a technique for noise compensation is proposed where an estimate of the noise envelope is subtracted from the noisy speech envelope. The noise compensation technique suppresses the effect of additive noise in speech. The robustness of the proposed features is further enhanced by the gain normalization technique. The normalized temporal envelopes are compressed with static (logarithmic) and dynamic (adaptive loops) compression and are converted into modulation frequency features. These features are used in an automatic phoneme recognition task. Experiments are performed in mismatched train/test conditions where the test data are corrupted with various environmental distortions like telephone channel noise, additive noise, and room reverberation. Experiments are also performed on large amounts of real conversational telephone speech. In these experiments, the proposed features show substantial improvements in phoneme recognition rates compared to other speech analysis techniques. Furthermore, the contribution of various processing stages for robust speech signal representation is analyzed.

1 January 2019 in Speech Communication
Verified
Journal Article
Closed access
AMAngel Mario Castro Martinez
Angel Mario Castro Martinez
LGLukas Gerlach
Lukas Gerlach
GPGuillermo Payá-Vayá
Guillermo Payá-Vayá
HHHynek Hermansky
Hynek Hermansky
JOJasper Ooster
Jasper Ooster
BMBernd T. Meyer
Bernd T. Meyer

3 January 2012 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
DWDaphna Weinshall
Daphna Weinshall
AZAlon Zweig
Alon Zweig
HHHynek Hermansky
Hynek Hermansky
SKStefan Kombrink
Stefan Kombrink
FOFrank W. Ohl
Frank W. Ohl
JBJoerg-Hendrik Bach
Joerg-Hendrik Bach
Unexpected stimuli are a challenge to any machine learning algorithm. Here, we identify distinct types of unexpected events when general-level and specific-level classifiers give conflicting predictions. We define a formal framework for the representation and processing of incongruent events: Starting from the notion of label hierarchy, we show how partial order on labels can be deduced from such hierarchies. For each event, we compute its probability in different ways, based on adjacent levels in the label hierarchy. An incongruent event is an event where the probability computed based on some more specific level is much smaller than the probability computed based on some more general level, leading to conflicting predictions. Algorithms are derived to detect incongruent events from different types of hierarchies, different applications, and a variety of data types. We present promising results for the detection of novel visual and audio objects, and new patterns of motion in video. We also discuss the detection of Out-Of-Vocabulary words in speech recognition, and the detection of incongruent events in a multimodal audiovisual scenario.