TAILIEUCHUNG - Báo cáo khoa học: "WordNet-based Semantic Relatedness Measures in Automatic Speech Recognition for Meetings"

This paper presents the application of WordNet-based semantic relatedness measures to Automatic Speech Recognition (ASR) in multi-party meetings. Different word-utterance context relatedness measures and utterance-coherence measures are defined and applied to the rescoring of N best lists. No significant improvements in terms of Word-Error-Rate (WER) are achieved compared to a large word-based ngram baseline model. We discuss our results and the relation to other work that achieved an improvement with such models for simpler tasks. . | WordNet-based Semantic Relatedness Measures in Automatic Speech Recognition for Meetings Michael Pucher Telecommunications Research Center Vienna Vienna Austria Speech and Signal Processing Lab TU Graz Graz Austria pucher@ Abstract This paper presents the application of WordNet-based semantic relatedness measures to Automatic Speech Recognition ASR in multi-party meetings. Different word-utterance context relatedness measures and utterance-coherence measures are defined and applied to the rescoring of N-best lists. No significant improvements in terms of Word-Error-Rate WER are achieved compared to a large word-based ngram baseline model. We discuss our results and the relation to other work that achieved an improvement with such models for simpler tasks. 1 Introduction As Pucher 2005 has shown different WordNet-based measures and contexts are best for word prediction in conversational speech. The JCN Section measure performs best for nouns using the noun-context. The LESK Section measure performs best for verbs and adjectives using a mixed word-context. Text-based semantic relatedness measures can improve word prediction on simulated speech recognition hypotheses as Demetriou et al. 2000 have shown. Demetriou et al. 2000 generated N-best lists from phoneme confusion data acquired from a speech recognizer and a pronunciation lexicon. Then sentence hypotheses of varying Word-Error-Rate WER were generated based on sentences from different genres from the British National Corpus BNC . It was shown by them that the semantic 129 model can improve recognition where the amount of improvement varies with context length and sentence length. Thereby it was shown that these models can make use of long-term information. In this paper the best performing measures from Pucher 2005 which outperform baseline models on word prediction for conversational telephone speech are used for Automatic Speech Recognition ASR in multi-party meetings. Thereby we want to .

• Báo cáo khoa học
• WordNet based Semantic Relatedness Measures
• Automatic Speech Recognition for Meetings
• Michael Pucher
• báo cáo khoa học
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Bài giảng Xử lý ngôn ngữ tự nhiên
• Ngôn ngữ tự nhiên
• Kỹ thuật lập trình
• Xử lý nhập nhằng ngữ nghĩa
• Xử lý ngữ nghĩa
• Xử lý ngôn ngữ
• Natural Language Processing
• Ngôn ngữ lập trình
• Nhập nhằng cấu trúc
• Tri thức về ngôn ngữ
• Mô hình n gram
• Dịch máy
• Phương pháp dịch máy
• Hiểu ngôn ngữ
• Phân tích ngữ nghĩa
• Phân loại tin tự động
• Biểu diễn vị từ
• Thuộc tính về sự kiện
• Thuộc tính về sự kiện
• Mô hình ngôn ngữ Google Book N grams
• Mô hình ngôn ngữ KenLM
• Phương pháp làm mịn
• Tách từ tiếng Việt
• Gán nhãn từ loại
• Phân tích cú pháp
• Nghĩa từ vựng
• Phân giải nhập nhằng từ
• Phân loại văn bản
• Lexical chain
• Phản hồi thông tin
• Bài toán PTCP
• Cấu trúc ngữ pháp
• Phân tích cú pháp xác suất
• CKY kết hợp xác suất
• Văn phạm phi ngữ cảnh xác suất
• Hình thái học