Acoustic separation between linguistic and extra-linguistic information in speech and its significant importance to enable speech communication
نویسنده
چکیده
あらまし 音声に含まれる音響的特徴の分離モデルとして,音声の生成過程に着眼し,音源と声道の特性に分離する ソース・フィルターモデルが従来より広く使われている。しかし,声道形状を音響的に表象するスペクトル包絡特性 は,本来独立な情報と考えられる音声の言語的情報と非言語的情報の両方に関与する。そのため,例えば,音声認識に おける不特定話者音響モデルは,同一の言語的情報を担う音声を大多数の話者から集め,統計的に音響モデリングを 行うことが一般的である。本稿の前半では,幼児の言語獲得における音声模倣行為,音声コミュニケーションの獲得に 困難を示す自閉症者の音声模倣行為,更には動物における音声模倣行為などを概観し,音声の中に同居する言語的情 報を担う特徴と非言語的情報を担う特徴とを音響的に分離するモデルの必要性を主張する。また,情報分離が不完全 な音響モデリングは,音声コミュニケーション能力の計算機上での実現を目的とした音響モデリングではなく,声帯 模写能力の計算機上での実現を目的とした音響モデリングとして解釈すべきであること,そして,不完全な情報分離 のみでは,本来,人間であっても音声コミュニケーションは困難となることについて言及する。本稿の後半では,二種 類の情報の分離を目的として筆者が近年提案している音声の構造的表象について触れ,幾つかの実験結果を紹介する。 キーワード ソース・フィルターモデル,言語的・非言語的情報,スペクトル包絡特性,音声コミュニケーション,音 声模倣と声帯模写,自閉症,音声の構造的表象,f -divergence に基づく完全変換不変性
منابع مشابه
A Study of the Relationship between Acoustic Features of “bæle” and the Paralinguistic Information
Language users benefit from special phonetic tools in order to communicate linguistic information as well as different emotional aspects and paralinguistic information through daily conversation. Having functions in conveying semantic information to listeners, prosodic features form the essential part of linguistic behavour, manipulating them potentially can play an important role in transmitt...
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 کاملAllophone-based acoustic modeling for Persian phoneme recognition
Phoneme recognition is one of the fundamental phases of automatic speech recognition. Coarticulation which refers to the integration of sounds, is one of the important obstacles in phoneme recognition. In other words, each phone is influenced and changed by the characteristics of its neighbor phones, and coarticulation is responsible for most of these changes. The idea of modeling the effects o...
متن کاملLinguistic Construction of a Winning Apology
The study analyzes the apology delivered by the then-democratic Presidential contender in 2007, Senator Barack H. Obama, to the Indian-American community. This apology succeeded in convincing American citizens of Obama’s goodwill and clean political standards, which eventually led him to surpass his chief opponent, Senator Hillary R. Clinton and become the President of the United States. The st...
متن کاملHuman Speech Model Based on Information Separation — Collection or Separation, That is the Question. —
— Collection or Separation, That is the Question. — Nobuaki Minematsu Graduate School of Information Science and Technology, The University of Tokyo [email protected] Abstract This paper points out that no existing technically-implemented speech model is adequate enough to describe one of the most fundamental and unique capacities of human speech processing. Language acquisition of infa...
متن کاملThe Role of Sociolinguistics in Second Language Acquisition
Learning a new language also involves learning a broad system of norms for social relations.This study broadly showed how EFL learners’ speech act is conveyed from their nativecultures when they are communicating in English and demonstrated that there are somepossibilities of cross-cultural misunderstanding when interlocutors are engaged in the speechact of complimenting with native speakers of...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2010