• Corpus ID: 12477217

A discriminative analysis within and across voiced and unvoiced consonants in neutral and whispered speech in multiple indian languages

  title={A discriminative analysis within and across voiced and unvoiced consonants in neutral and whispered speech in multiple indian languages},
  author={Nisha Meenakshi and Prasanta Kumar Ghosh},
Whispered speech lacks the vocal chord vibration which is typically used to distinguish voiced and unvoiced consonants, making their discrimination a challenging task. In this work, we objectively and subjectively quantify the amount of discrimination between a voiced (V) consonant and its unvoiced (UV) counterpart using seven V-UV consonant pairs in six Indian languages, in neutral and whispered speech. We also quantify the extent to which the voicing characteristics in a consonant changes… 

Figures and Tables from this paper

A Robust Voiced/Unvoiced Phoneme Classification from Whispered Speech Using the 'Color' of Whispered Phonemes and Deep Neural Network
A robust method to perform framelevel classification of voiced (V) and unvoiced (UV) phonemes from whispered speech, a challenging task due to its voiceless and noise-like nature is proposed.
Analysis of whispered speech and its conversion to neutral speech
Whispering is an indispensable form of communication that emerges in private conversations as well as in pathological situations [1]. In conditions such as partial or total laryngectomy, spasmodic
Whispered Speech to Neutral Speech Conversion Using Bidirectional LSTMs
A bidirectional long short-term memory based whispered speech to neutral speech conversion system that employs the STRAIGHT speech synthesizer reveals that the proposed method yields a more natural sounding neutral speech from whispered speech.
SilentVoice: Unnoticeable Voice Input by Ingressive Speech
The proposed "ingressive speech" method enables placement of a microphone very close to the front of the mouth without suffering from pop-noise, capturing very soft speech sounds with a good S/N ratio.


Acoustic analysis of consonants in whispered speech.
  • S. Jovicic, Z. Saric
  • Physics, Linguistics
    Journal of voice : official journal of the Voice Foundation
  • 2008
Lip Kinematics for /p/ and /b/ Production during Whispered and Voiced Speech
The results revealed that mean peak opening and closing velocities for /b/ were significantly greater than those for /p/ during whispered speech, which supported the suggestion that whispered speech and voiced speech rely on distinct motor control processes.
The role of tongue articulation for /s/ and /z/ production in whispered speech
Although the timing of the initiation and cessation of vocal fold vibrations is crucial to characterize the voiced and voiceless cognates, other cues, such as the duration of preceding vowels, the
Analysis and recognition of whispered speech
Analysis and classification of speech mode: whispered through shouted
This is the first study to collectively consider the five speech modes: whispered, soft, neutral, loud and shouted, which can provide improved speech/speaker modeling information, as well as classified vocal mode knowledge to improve speech and language technology in real scenarios.
Closure and constriction duration for alveolar consonants during voiced and whispered speaking conditions.
Spectrographic analysis of steady‐state portions of vowels and closure and constriction durations for consonants revealed significant durational differences associated with speaking conditions for /t, d, s, z, i, a/.
Speaker Identification Within Whispered Speech Audio Streams
  • Xing Fan, J. Hansen
  • Physics
    IEEE Transactions on Audio, Speech, and Language Processing
  • 2011
A seamless neutral/whisper mismatched closed-set speaker recognition system based on an Mel-frequency cepstral coefficient-Gaussian mixture model (MFCC-GMM) framework and an alternative feature extraction algorithm based on linear and exponential frequency scales is applied.
What's in a whisper?
  • V. Tartter
  • Physics
    The Journal of the Acoustical Society of America
  • 1989
Untrained listeners identified 18 different whispered initial consonants significantly better than chance in nonsense syllables and the phonetic features of place and manner of articulation and, to a lesser extent, voicing were correctly identified.
Bilabial closure durations for p, b, and m in voiced and whispered vowel environments.
  • M. F. Schwartz
  • Physics
    The Journal of the Acoustical Society of America
  • 1972
The results indicated significantly greater whisper durations for /p/ and /b/ but not /m/.
Male and female voice quality and its relationship to vowel formant frequencies.
  • R. Coleman
  • Physics
    Journal of speech and hearing research
  • 1971
Speech samples obtained from a group of adult males and females while they articulated the tone produced by a single-frequency electrolarynx were played to a panel of listeners who were asked to de...