Incorporating Speech Recognition Confidence into Discriminative Named Entity Recognition of Speech Data
نویسندگان
چکیده
This paper proposes a named entity recognition (NER) method for speech recognition results that uses confidence on automatic speech recognition (ASR) as a feature. The ASR confidence feature indicates whether each word has been correctly recognized. The NER model is trained using ASR results with named entity (NE) labels as well as the corresponding transcriptions with NE labels. In experiments using support vector machines (SVMs) and speech data from Japanese newspaper articles, the proposed method outperformed a simple application of textbased NER to ASR results in NER Fmeasure by improving precision. These results show that the proposed method is effective in NER for noisy inputs.
منابع مشابه
Discriminative named entity recognition of speech data using speech recognition confidence
This paper presents a method for the named entity recognition (NER) of speech data that uses automatic speech recognition (ASR) confidence as a feature that indicates whether each word is correctly recognized. An NER model is trained using ASR results with named entity (NE) labels to include an ASR confidence feature as well as corresponding transcriptions with NE labels. Experiments using supp...
متن کاملIncorporating named entity recognition into the speech transcription process
Named Entity Recognition (NER) from speech usually involves two sequential steps: transcribing the speech using Automatic Speech Recognition (ASR) and annotating the outputs of the ASR process using NER techniques. Recognizing named entities in automatic transcripts is difficult due to the presence of transcription errors and the absence of some important NER clues, such as capitalization and p...
متن کاملPersian Phone Recognition Using Acoustic Landmarks and Neural Network-based variability compensation methods
Speech recognition is a subfield of artificial intelligence that develops technologies to convert speech utterance into transcription. So far, various methods such as hidden Markov models and artificial neural networks have been used to develop speech recognition systems. In most of these systems, the speech signal frames are processed uniformly, while the information is not evenly distributed ...
متن کاملAn Information-Theoretic Discussion of Convolutional Bottleneck Features for Robust Speech Recognition
Convolutional Neural Networks (CNNs) have been shown their performance in speech recognition systems for extracting features, and also acoustic modeling. In addition, CNNs have been used for robust speech recognition and competitive results have been reported. Convolutive Bottleneck Network (CBN) is a kind of CNNs which has a bottleneck layer among its fully connected layers. The bottleneck fea...
متن کاملImproving named entity recognition with prosodic features
In natural language processing (NLP) the problem of named entity (NE) recognition in speech is well known, yet remains a challenge where performance is dependent on automatic speech recognition (ASR) system error rates. NEs are often foreign or out-of-vocabulary (OOV) words, leaving conventional ASR systems unable to recognize them. In our research, we improve a CRF-based NE recognition system ...
متن کامل