Toshimitsu Minowa

Method and apparatus for speech synthesis whereby waveform segments expressing respective syllables of a speech item are modified in accordance with rhythm, pitch and speech power patterns expressed by a prosodic template

A method and apparatus for speech synthesis utilize a plurality of stored prosodic templates, each having been generated based on a series of enunciations of a single syllable executed in accordance with the rythm, pitch and speech power variations of an enunciated sample speech item, whereby the templates express rythm, speech power and pitch characteristics of respectively different sample speech items. Data representing an object speech item are converted to a sequence of acoustic waveform segments which respectively express the syllables of the speech item, the number of morae (syllable intervals) and the accent type of the speech item are judged and a prosodic template having the same number of morae and accent type is selected, and waveform shaping is applied to the waveform segments such as to match the rythm, speech power and pitch characteristics of the object speech item to those expressed by the selected prosodic template. The shaped acoustic waveform segments are then linked to form a continuous acoustic waveform, thereby obtaining synthesized speech which closely resembles natural speech.

The Japanese CV-Syllable positioning rule for speech synthesis

In the inspection of the time intervals between two adjacent estimated Auditory Perceptual Timing Points (APTP), the time intervals were found to be dependent on the succeeding CV-syllable in continuously uttered sentences. In order to precisely investigate this dependency, the time intervals corresponding to the specified succeeding CV-syllables were measured by means of listening tests and the t-test was carried out. Furthermore, the effects of exceptional sounds were taken into consideration. Then a new rule for controlling the rhythm of synthetic speech by positioning each CV-syllable at an adequate time position was developed. The speech synthesized according to the positioning rule were evaluated and the result showed that 70% to 80% of listeners recognized its superiority.

A study on designing the amplitude gain of the feedback loop of an electroacoustic system.

The acoustic feedback from a loudspeaker to a microphone forms a closed loop and is the cause of instability (howling). When the electrical amplifier gain is fixed on maximum within a designed range, it is the excess amplitude of the open‐loop gain over the unity (0 dB) that should be minimized by a howling suppression technique. It can be designed using a diffuse sound field model [Diestel, J. Acoust. Soc. Am. 35, 2019–2022 (1963)]. According to this method, the designed value was 18–24 dB in the case of a single loudspeaker and single microphone system located in a room with dimensions of 10×20×6 m and sound absorption coefficient of 0.05–0.5 and the gain of the electrical amplifier being fixed so that the farthest located attendant from the loudspeaker could perceive 62.9 dB (SPL). In order to evaluate the result, measurements were carried out in a conference room.

Rhythm control based on CV‐syllable positioning for Japanese synthetic speech

A technique has been developed for Japanese speech synthesis‐by‐rule to control the rhythm of synthetic speech sounds to which little attention has been given so far. In Japanese speech sounds, syllables are generally believed to be the basic elements of the rhythm, with each syllable sound pronounced almost isochronously. It was found through listening tests that there is an important portion in a syllable for recognizing the syllable and the positioning of that portion determines the rhythm. The portion was termed auditory perceptual timing point (APTP) and was determined for each syllable in listening tests. Most APTPs were found near the voice onset, which closely agreed with the result obtained by Sato [H. Sato, Trans. Comm. Speech Res., ASJ, S77‐31, 1–8 (1977)]. The rhythm pattern was, in principle, determined by the number of morae in individual words and the syntactic structure of an input text, though further investigation is necessary to construct detailed rules. It has been confirmed that the q...