New waves of consumer-centric applications, such as voice search and voice interaction with mobile devices and home entertainment systems, increasingly require automatic speech recognition (ASR) to be robust to the full range of real-world noise and other acoustic distorting conditions. Despite its practical importance, however, the inherent links between and distinctions among the myriad of methods for noise-robust ASR have yet to be carefully studied in order to advance the field further. To this end, it is critical to establish a solid, consistent, and common mathematical foundation for noise-robust ASR, which is lacking at present. This article is intended to fill this gap and to provide a thorough overview of modern noise-robust techniques for ASR developed over the past 30 years. We emphasize methods that are proven to be successful and that are likely to sustain or expand their future applicability. We distill key insights from our comprehensive overview in this field and take a fresh look at a few old problems, which nevertheless are still highly relevant today. Specifically, we have analyzed and categorized a wide range of noise-robust techniques using five different criteria: 1) feature-domain vs. model-domain processing, 2) the use of prior knowledge about the acoustic environment distortion, 3) the use of explicit environment-distortion models, 4) deterministic vs. uncertainty processing, and 5) the use of acoustic models trained jointly with the same feature enhancement or model adaptation process used in the testing stage. With this taxonomy-oriented review, we equip the reader with the insight to choose among techniques and with the awareness of the performance-complexity tradeoffs. The pros and cons of using different noise-robust ASR techniques in practical application scenarios are provided as a guide to interested practitioners. The current challenges and future research directions in this field is also carefully analyzed.

/pdf/an-overview-of-noise-robust-automatic-speech-recognition-u8zbz18oa3.pdf

An overview of noise-robust automatic speech recognition

According to the invention, speech recognition can be limited to a smaller number making use of commands (16, 17) given by a user. By means of a method and device, according to the invention, it is also possible to activate a speech recognition device by making use, in the activation, of an existing keyboard or a touch-sensitive screen of the device. A method, according to the invention, provides the user with a logical way to activate the speech recognition device in the device simultaneously providing an improved capacity of the speech recognition device. According to the invention, it is also possible to carry out the speech recognition process by making use of commands given by the user irrespective of how the speech recognition device itself is activated. According to an embodiment of the invention, the device comprises a touch-sensitive screen or surface, in which case the information about a single letter or several letters written on the screen is transmitted to the speech recognition device, whereupon speech recognition is limited to words, wherein the letters in question occur. Speech recognition is most preferably limited to a name beginning with the letter written on the touch screen by the user.

Method and a device for recognizing speech

The addition of a word normalized energy contour uniformly improves performance of the HMM recognizer and makes it more robust to di erence in talker populations. This kind of normalization generally requires some information on the statistics of energy features over the whole utterance, which is not a feasible solution in real-time applications due to the unnecessary long processing delay. In this paper, we propose a more e cient implementation approach for energy feature normalization where the normalization coe cients are computed using a look-a-head delay of xed length. The experimental results on German connected digit recognition task show that a 12% string error rate reduction is obtained by using a look-a-head delay energy normalization scheme when compared to without using the energy feature. Further reduction of 10% string error rate is achieved by integrating the speech/nonspeech decision mechanism.

Robust energy normalization using speech/nonspeech discriminator for German connected digit recognition.

A new subband based speech enhancement scheme is presented. It integrates spatial and temporal signal processing methods to enhance speech signals in a noisy environment. The approach makes use of the popular blind signal separation (BSS) to spatially separate the target signal from the interference. Due to the multipath/reverberant environment, BSS has its fundamental limitation in its separation quality. To overcome that, an adaptive noise canceller (ANC) is employed to perform further interference reduction. The reference for the ANC in this case is simply the interference dominant output from the BSS. A higher order statistical method is proposed for the selection of the reference signal. This post processing acts as a spectral decorrelator and experimental results show that even in under-determined (more sources than elements) case, the structure offers impressive enhancement capability. Further, a remarkable improvement in recognition rate is registered when tested in automatic speech recognition (ASR).

Convolutive blind signal separation with post-processing

This paper presents a multi-lingual speaker-independent voice User Interface (UI) that has been implemented for Nokia S60 mobile phones. The paper concentrates on discussing the specific approach used for achieving a multi-lingual and configurable speech recognition and speech synthesis system. The main applications are speaker-independent name dialing and voice commands. The novelty of the applications is that the user does not need to train the voice dialing system but the application reads the user's phonebook and generates the required voice tags automatically. The speaker-independent voice dialing has already been introduced in regions where the language diversity is not so great. The system presented in this paper is the first of its kind to support both speech recognition and speech synthesis in more than 40 languages in embedded devices with strict memory and performance requirements.

Multi-Lingual Speaker-Independent Voice User Interface For Mobile Devices

The acoustic mismatch between testing and training conditions is known to severely degrade the performance of speech recognition systems. Segmental feature vector normalization was found to improve the noise robustness of mel-frequency cepstral coefficients (MFCC) feature vectors and to outperform other state-of-the-art noise compensation techniques in speaker-dependent recognition. The objective of feature vector normalization is to provide environment-independent parameter statistics in all noise conditions. We propose a more efficient implementation approach for feature vector normalization where the normalization coefficients are computed in a recursive way. Speaker-dependent recognition experiments show that the recursive normalization approach obtains over 60%, the segmental method approximately 50%, and parallel model combination a 14% overall error rate reduction, respectively. Moreover, in the recursive case, this performance gain is obtained with the smallest implementation costs. Also in speaker-independent connected digit recognition, over a 16% error rate reduction is obtained with the proposed feature vector normalization approach.

K. Laurila

Papers

A recursive feature vector normalization approach for robust speech recognition in noise