160 likes | 550 Vues
Speech Communications. Chapter 7. Speech Communications. The Nature of Speech Criteria for Evaluating Speech Components of Speech Communication System Synthesized Speech . The Nature of Speech 1/2. 發聲 : 呼吸系統 , Articulators Types of Speech Sound Phoneme ( 音素 )
E N D
Speech Communications Chapter 7
Speech Communications • The Nature of Speech • Criteria for Evaluating Speech • Components of Speech Communication System • Synthesized Speech
The Nature of Speech 1/2 • 發聲: 呼吸系統, Articulators • Types of Speech Sound • Phoneme (音素) • shortest segment of speech if change → meaning change • 分類: 母音 (vowel), 子音 (consonant) 雙母音 (diphthongs) • Phoneme →Syllable →Word → Sentence
The Nature of Speech 2/2 • Depicting Speech • Waveform, Spectrum • Sound spectrogramFig 8-1 • Intensity of Speech • Average intensity (speech power): 母音>子音 • Intelligibility: 子音較重要 • Frequency Composition of Speech • 低頻: 男>女Fig 8-2 • Shouting: frequency上升
Criteria for Evaluating Speech • Speech Intelligibility (能解度) • 方法 • Repeat 呈現的聲音 • 回答問題 • Test • Nonsense syllables • Isolated words (phonetically balanced, PB) • Sentences • Speech quality (Naturalness) • Preference
Components of Speech Communication System • Speaker • Message • Transmission System • Noise • Hearer
Components of Speech Communication System • Speaker • Enunciation (清晰的聲音) • Superior Speakers • Longer syllable duration • Greater intensity • More total time with speech sounds • Frequencies varied 1/7
Components of Speech Communication System • Message • Phoneme Confusion • DVPBGCET, FXSH, KJA, MN • Avoid single letters, Word-spelling alphabet • Word Characteristics • Familiar words • Long words 2/7
Components of Speech Communication System • Message • Context Features • Sentence: meaningful>nonsense • Set size: 字多<字少 Fig 7-3 • Guidelines • 用較少的字 • Standard sentence • Avoid short word • Familiarize user 3/7
Components of Speech Communication System • Transmission System • Filtering (Frequency distortion) Fig 7-4 • High-pass: cutoff<600 Hz • Low-pass: cutoff>4000 Hz • Amplitude Distortion Fig 7-57-6 • Peak clipping Quality, Intelligibility ≈ • Center clipping Intelligibility • 提高 Intelligibility: Peak clipping Amplify (子音/母音) 4/7
Components of Speech Communication System • Noise • Articulation Index (AI)Fig 7-7 • 1/3 octave, S-N, weighted sum • Intelligibility Fig 7-8Tab 7-1 • Preferred-Octave Speech Interference Level (PSIL) • Mean of 500, 1000, 2000 Hz (octave) • SIL: Mean of 600-1200, 1200-2400, . . . • Intelligibility (vs. distance) Fig 7-9 • Subjective rating Fig 7-10Tab 7-2 5/7
Components of Speech Communication System • Noise • Preferred Noise Criterion Curve (PNC) Fig 7-11Tab 7-3 • Reverberation Fig 7-12 • Reverberation time: Decay 60 dB • Reverberation time Intelligibility 6/7
Components of Speech Communication System • Hearer • Age Fig 7-13 • Wearing of Hearing Protection 7/7
Synthesized Speech • 種類 • Uses • Performance • Preference • Guidelines
Synthesized Speech • 種類 • Synthesis by Analysis • Digitized human speech compressed data format • 缺點: 限於 encoded & stored Lack of coarticulation • Synthesis by Rule • 缺點: quality 較差