Among various training concepts for speaker adaptation, Speaker Adaptive Training (SAT) has been successfully applied to a standard Hidden Markov Model (HMM) speech recognizer, whose state is associated with Gaussian Mixture Models (GMMs). On the other hand, focusing on the high discriminative power of Deep Neural Networks (DNNs), a new type of speech recognizer structure, which combines DNNs and HMMs, has been vigorously investigated in the speaker adaptation research field. Along these two lines, it is natural to conceive of further improvement to a DNN-HMM recognizer by employing the training concept of SAT. In this paper, we propose a novel speaker adaptation scheme that applies SAT to a DNN-HMM recognizer. Our SAT scheme allocates a Speaker Dependent (SD) module to one of the intermediate layers of DNN, treats its remaining layers as a Speaker Independent (SI) module, and jointly trains the SD and SI modules while switching the SD module in a speaker-by-speaker manner. We implement the scheme using a DNN-HMM recognizer, whose DNN has seven layers, and elaborate its utility over TED Talks corpus data. Our experimental results show that in the supervised adaptation scenario, our Speaker-Adapted (SA) SAT-based recognizer reduces the word error rate of the baseline SI recognizer and the lowest word error rate of the SA SI recognizer by 8.4% and 0.7%, respectively, and by 6.4% and 0.6% in the unsupervised adaptation scenario. The error reductions gained by our SA-SAT-based recognizers proved to be significant by statistical testing. The results also show that our SAT-based adaptation outperforms, regardless of the SD module layer selection, its counterpart SI-based adaptation, and that the inner layers of DNN seem more suitable for SD module allocation than the outer layers.

The performance of English automatic speech recognition systems decreases when recognizing spontaneous speech mainly due to multiple pronunciation variants in the utterances. Previous approaches address this problem by modeling the alteration of the pronunciation on a phoneme to phoneme level. However, the phonetic transformation effects induced by the pronunciation of the whole sentence have not yet been considered. In this article, the sequence-based pronunciation variation is modeled using a noisy channel approach where the spontaneous phoneme sequence is considered as a “noisy” string and the goal is to recover the “clean” string of the word sequence. Hereby, the whole word sequence and its effect on the alternation of the phonemes will be taken into consideration. Moreover, the system not only learns the phoneme transformation but also the mapping from the phoneme to the word directly. In this study, first the phonemes will be recognized with the present recognition system and afterwards the pronunciation variation model based on the noisy channel approach will map from the phoneme to the word level. Two well-known natural language processing approaches are adopted and derived from the noisy channel model theory: Joint-sequence models and statistical machine translation. Both of them are applied and various experiments are conducted using microphone and telephone of spontaneous speech.

The performance of speech translation systems combining automatic speech recognition (ASR) and machine translation (MT) systems is degraded by redundant and irrelevant information caused by speaker disfluency and recognition errors. This paper proposes a new approach to translating speech recognition results through speech consolidation, which removes ASR errors and disfluencies and extracts meaningful phrases. A consolidation approach is spun off from speech summarization by word extraction from ASR 1-best. We extended the consolidation approach for confusion network (CN) and tested the performance using TED speech and confirmed the consolidation results preserved more meaningful phrases in comparison with the original ASR results. We applied the consolidation technique to speech translation. To test the performance of consolidation-based speech translation, Chinese broadcast news (BN) speech in RT04 were recognized, consolidated and then translated. The speech translation results via consolidation cannot be directly compared with gold standards in which all words in speech are translated because consolidation-based translations are partial translations. We would like to propose a new evaluation framework for partial translation by comparing them with the most similar set of words extracted from a word network created by merging gradual summarizations of the gold standard translation. The performance of consolidation-based MT results was evaluated using BLEU. We also propose Information Preservation Accuracy (IPAccy) and Meaning Preservation Accuracy (MPAccy) to evaluate consolidation and consolidation-based MT. We confirmed that consolidation contributed to the performance of speech translation.

In this paper, we propose a new method of automatic speech summarization for each utterance, where a set of words that maximizes a summarization score is extracted from automatic speech transcriptions. The summarization score indicates the appropriateness of summarized sentences. This extraction is achieved by using a dynamic programming technique according to a target summarization ratio. This ratio is the number of characters/words in the summarized sentence divided by the number of characters/words in the original sentence. The extracted set of words is then connected to build a summarized sentence. The summarization score consists of a word significance measure, linguistic likelihood, and a confidence measure. This paper also proposes a new method of measuring summarization accuracy based on a word network expressing manual summarization results. The summarization accuracy of each automatic summarization is calculated by comparing it with the most similar word string in the network. Japanese broadcast-news speech, transcribed using a large-vocabulary continuous-speech recognition (LVCSR) system, is summarized and evaluated using our proposed method with 20, 40, 60, 70 and 80% summarization ratios. Experimental results reveal that the proposed method can effectively extract relatively important information by removing redundant or irrelevant information.