We present a system which automatically reduces the ringtone volume as soon as users start picking up their mobile devices to answer incoming phone calls. Our system uses multiple sensors already in mobile phones (e.g. accelerometer, gyroscope, and proximity sensor) to extract 47 features, and uses supported vector machine (SVM) as the classifier to identify the act of picking up a phone. We have collected data under several typical conditions: including walking vs stationary and picking up the phone from inside a bag vs pockets. Our results show that the system can correctly identify users picking up their mobile phones 95% of the time on average.

This paper presents a set of corpus-based text-to-speech synthesis technologies for Mandarin Chinese. A large speech corpus produced by a single speaker is used, and the speech output is. synthesized from waveform units of variable lengths, with desired linguistic properties, retrieved from this corpus. Detailed methodologies were developed for designing "phonetically rich" and "prosodically rich" corpora by automatically selecting sentences from a large text corpus to include as many desired phonetic combinations and prosodic features as possible. Automatic phonetic labeling with iterative correction rules and automatic prosodic labeling with a multi-pass top-down procedure were also developed such that the labeling process for the corpora can be completely automatic. A hierarchical prosodic structure for an arbitrary desired text sentence is then generated based on the identification of different levels of break indices, and the prosodic feature sets and appropriate waveform units are finally selected and retrieved from the corpus, modified if necessary, and concatenated to produce the output speech. The special structure of Mandarin Chinese has been carefully considered in all these technologies, and preliminary assessments indicated very encouraging synthesized speech quality.

Chinese language has quite different characteristic structures from those of English. There are at least word, character, syllable, Initial-Final levels in Chinese, each carrying different levels of information with complicated correlations among them. In this paper, we investigate the dependency of pronunciation variation in conversational Mandarin speech on these different levels under various contextual conditions considering the structural features of the language. The influence of speaking rate and word frequency on such pronunciation variation is also analyzed. Different pruning methods, for including pronunciation variation in speech recognition were also evaluated, and the experimental results showed that improved accuracy is obtainable if the characteristics of the pronunciation variation found in the analysis can be properly taken into account. All discussions here are based on tests with the LDC Mandarin Call Home corpus.

This paper presents a new approach to improve the conventional eigenvoice technique. In the conventional eigenvoice, an eigenspace is established by introducing a priori training speakers via PCA. The adaptation data is then used to determine a group of coefficients with respect to the eigenspace and build the SD model for the testing speaker. In the proposed approach, the eigenspace in the conventional eigenvoice is segmented into N sub-eigenspaces. Each subeigenspace is established by those components in the training speaker SD models with similar properties to each other. With the adaptation data, N groups of coefficients corresponding to the N sub-eigenspaces can be determined to build SD model for the new testing speaker. Here, both mixture-based and feature-based segmentation of eigenspace were tested, and improved results compared to the conventional eigenvoice were obtained in both cases. Even better results were obtained when these approaches were properly combined.

The removal of noise from speech signals has applications ranging from speech enhancement for cellular communications to front ends for speech recognition systems. In this paper, we present a new nonlinear time-domain method called Noise-Regularized Adaptive Filtering. The approach is based on minimum mean-squared estimation using a modified cost function and allows designing both linear and nonlinear filters using only the observed noisy speech. 1. A GENERAL FRAMEWORK FOR MMSE ESTIMATION Given a noisy speech signal,

This paper describes an improved concatenative synthesis module for a Chinese text-to-speech system. The concatenated segments are on-line selected from a designed speech corpus that is precisely segmented with an improved version of HMMs. The selection criteria are the prosodic and contextual similarities between the units and the desired targets from the previous module of the TTS system. The TD-PSOLA modifies the prosodic parameters of the selected units, and three methods for unit concatenation are performed according to the types of the syllabic junctures. These types are classified with the knowledge from the phonetic observations of large amounts of speech data. The output speech is remarkably fluent and natural because the coarticulation effects cross syllabic boundaries are well modeled and less prosodic modification is needed for the TD-PSOLA.

This paper presents a new Chinese text-to-speech system that produces very natural and intelligible synthetic Mandarin speech based on part-of-speech analysis, prosodic modeling and non-uniform units. The distinguishing features and key technology for the system can be summarized as follows. (1) A text analysis module for word identification and tagging was developed based on part-of-speech modeling and using heuristic rules to achieve very high accuracy. (2) The required prosodic parameters for the synthetic speech are derived from a two-stage procedure. The prosodic structures of the input texts are first derived from a statistical model trained by a large speech database, and the prosodic parameters are then determined according to the structures. (3) A specially designed speech segments inventory constructed with non-uniform and pitch dependent units is used to improve the fluency and intelligibility of the system.

A key problem for today's speech synthesis technology is to automatically generate an appropriate hierarchical prosodic structure for text input and incorporate it into synthesized sptech[l][2].This paper presents a method for such a problem in Mandarin Chinese.This method uses a speech database for the training of a statistical model to generate the prosodic structure and determine prosodic parameten such as syllable duration, pause, energy and intonation.The experimental results show that an accuraq of 83.1% in the prediction of prosodic structure can be achieved.Furthermore, a Chinese text-to-pech system can be developed based on the proposed prosodic st"Te.