In this paper, we consider the use of multiple acoustic features of the speech signal for robust speech recognition. We investigate the combination of various auditory based (Mel Frequency Cepstrum Coefficients, Perce...
详细信息
We present first results using paraphrase as well as textual entailment data to test the language universal constraint posited by Wu's (1995, 1997) Inversion Transduction Grammar (ITG) hypothesis. In machine trans...
详细信息
We directly investigate a subject of much recent debate: do word sense disambigation models help statistical machine translation quality? We present empirical results casting doubt on this common, but unproved, assump...
详细信息
Semantic relations between text concepts denote the core elements of lexical semantics. This paper presents a model for the automatic detection of INTENTION semantic relation. Our approach first identifies the syntact...
详细信息
作者：
Wu, DekaiDepartment of Computer Science
HKUST Human Language Technology Center Hong Kong University of Science and Technology Clear Water Bay Kowloon Hong Kong
We offer a perspective on EBMT from a statistical MT standpoint, by developing a three-dimensional MT model space based on three pairs of definitions: (1) logical versus statistical MT, (2) schema-based versus example...
详细信息
We give an overview of the RWTH phrase-based statistical machine translation system that was used in the evaluation campaign of the International Workshop on Spoken language Translation 2005. We use a two pass approac...
详细信息
In this paper, we consider the use of multiple acoustic features of the speech signal for continuous speech recognition. A novel articulatory motivated acoustic feature is introduced, namely the spectrum derivative fe...
详细信息
In this paper, we consider the use of multiple acoustic features of the speech signal for continuous speech recognition. A novel articulatory motivated acoustic feature is introduced, namely the spectrum derivative feature. The new feature is tested in combination with the standard Mel Frequency Cepstral Coefficients (MFCC) and the voicedness features. Linear Discriminant Analysis is applied to find the optimal combination of different acoustic features. Experiments have been performed on small and large vocabulary tasks. Significant improvements in word error rate have been obtained by combining the MFCC feature with the articulatory motivated voicedness and spectrum derivative features: improvements of up to 25% on the small-vocabulary task and improvements of up to 4% on the large-vocabulary task relative to using MFCC alone with the same overall number of parameters in the system.
In the last decade, the statistical approach has found widespread use in machine translation both for written and spoken language and has had a major impact on the translation accuracy. The goal of this paper is to co...
详细信息
In the last decade, the statistical approach has found widespread use in machine translation both for written and spoken language and has had a major impact on the translation accuracy. The goal of this paper is to cover the state of the art in statistical machine translation. We would re-visit the underlying principles of the statistical approach to machine translation and summarize the progress that has been made over the last decade
In this paper, we consider the use of multiple acoustic features of the speech signal for robust speech recognition. We investigate the combination of various auditory based (mel frequency cepstrum coefficients, perce...
详细信息
In this paper, we consider the use of multiple acoustic features of the speech signal for robust speech recognition. We investigate the combination of various auditory based (mel frequency cepstrum coefficients, perceptual linear prediction, etc.) and articulatory based (voicedness) features. Features are combined by linear discriminant analysis and log-linear model combination based techniques. We describe the two feature combination techniques and compare the experimental results. Experiments performed on the large-vocabulary task VerbMobil II (German conversational speech) show that the accuracy of automatic speech recognition systems can be improved by the combination of different acoustic features.
This paper describes Mocha, an open mobile S/W platform and application developed by Samsung Electronics. Mocha's key features are its efficiency (it fits in regular phones), its portability (it covers different s...
详细信息
This paper describes Mocha, an open mobile S/W platform and application developed by Samsung Electronics. Mocha's key features are its efficiency (it fits in regular phones), its portability (it covers different stack/OS/chipsets for CDMA, EV-DO, GSM/GPRS, and UMTS), its modularity and configurability (it meets customers' varying needs), its extensibility (it can he adapted to include new features and interfaces), its interoperability based on de-facto standards such as OMA, 3GPP, 3GPP2, CDG; and its security (it can withstand the attack of malicious applications). Among these key features, in this paper, we outline the multimedia messaging service (MMS) that inspired this system and then describe its design, architecture, and prototype implementation.
暂无评论