Massachusetts Institute of Technology

Thomas F Quatieri, Jr

Robert J McAulay

Nicolas Malyska

Andrea Carolina Trevino

Tianyu Wang

Gerald C O'Leary

A system and a method for assessing a condition in a subject. Phones from speech of the subject are recognized, one or more prosodic or speech-excitation-source features of the phones are extracted, and an assessment of a condition of the subject, is generated based on a correlation between the features of the phones and the condition.

Phonologically-based biomarkers for major depressive disorder

The present invention relates to co-channel audio source separation. In one embodiment a first frequency-related representation of plural regions of the acoustic signal is prepared over time, and a two-dimensional transform of plural two-dimensional localized regions of the first frequency-related representation, each less than an entire frequency range of the first frequency related representation, is obtained to provide a two-dimensional compressed frequency-related representation with respect to each two dimensional localized region. For each of the plural regions, at least one pitch is identified. The pitch from the plural regions is processed to provide multiple pitch estimates over time. In another embodiment, a mixed acoustic signal is processed by localizing multiple time-frequency regions of a spectrogram of the mixed acoustic signal to obtain one or more acoustic properties. A separate pitch estimate of each of the multiple acoustic signals at a time point are provided by combining the one or more acoustic properties. At least one of the multiple acoustic signals is recovered using the separate pitch estimates.

Method and apparatus for audio source separation

Acoustic signals are analyzed by two-dimensional (2-D) processing of the one-dimensional (1-D) speech signal in the time-frequency plane. The short-space 2-D Fourier transform of a frequency-related representation (e.g., spectrogram) of the signal is obtained. The 2-D transformation maps harmonically-related signal components to a concentrated entity in the new 2-D plane (compressed frequency-related representation). The series of operations to produce the compressed frequency-related representation is referred to as the 'grating compression transform' (GCT), consistent with sine-wave grating patterns in the frequency-related representation reduced to smeared impulses. The GCT provides for speech pitch estimation. The operations may, for example, determine pitch estimates of voiced speech or provide noise filtering or speaker separation in a multiple speaker acoustic signal.

2-D processing of speech

Encoding techniques and devices are based on a sinusoidal speech representation model. In one aspect of the invention, a pitch-adaptive channel encoding technique for amplitude coding varies the channel spacing in accordance with the pitch of the speaker's voice. In another aspect of the invention, a phase synthesis technique locks rapidly-varying phases into synchrony with the phase of the fundamental. Phase coding techniques which introduce a voice-dependent random phase and a pitch-adaptive quadratic phase dispersion are also performed.

Coding of acoustic waveforms

Methods and apparatus for reducing discontinuities between frames of sinusoidally modeled acoustic waveforms, such as speech, which occur when sampling at low frame rates. A Fast Fourier Transform-based overlap-add technique is applied to amplitude, frequency and phase components of sinusoidal waves after frame-to-frame sine wave matching has been performed. Matched sine wave amplitudes and frequencies are linearly interpolated and mid-point phase is estimated such that the mid-frame sine wave is best fit to the most recent half-frame segments of the lagging and leading sine waves. Synthetic mid-frame sine waves are generated using the interpolated amplitude and frequency and estimated phase values. Synthesized acoustic waveforms of high quality from original source waveforms can be produced in sinusoidal analysis/synthesis operations at coding frame rates of 50 Hz and lower. The methods and devices disclosed herein are particularly useful for computationally efficient coding and synthesis of speech waveforms.

Computationally efficient sine wave synthesis for acoustic waveform

A sinusoidal model for acoustic waveforms is applied to develop a new analysis/synthesis technique which characterizes a waveform by the amplitudes, frequencies, and phases of component sine waves. These parameters are estimated from a short-time Fourier transform. Rapid changes in the highly-resolved spectral components are tracked using the concept of 'birth' and 'death' of the underlying sine waves. The component values are interpolated from one frame to the next to yield a respresentation that is applied to a sine wave generator. The resulting synthetic waveform preserves the general waveform shape and is perceptually indistinguishable from the original. Furthermore, in the presence of noise the perceptual characteristics of the waveform as well as the noise are maintained. The method and devices are particularly useful in speech coding, time-scale modification, frequency scale modification and pitch modification.

Processing of acoustic waveforms

A lower threshold for dynamic range compression and clipping is allowed by sinusoidal estimation and phase adjustment of the original speech signal to obtain a lower Peak to RMS ratio. A sinusoidal speech representation system is applied to the problem of speech dispersion by pre-processing the waveform prior to transmission to reduce the peak-to-RMS ratio of the waveform. The sinusoidal system first estimates and then removes the natural phase dispersion in the frequency components of the speech signal. Artificial dispersion based on pulse compression techniques is then introduced with little change in speech quality. The new phase dispersion allocation serves to preprocess the waveform prior to dynamic range compression and clipping, allowing considerably deeper thresholding than can be tolerated on the original waveform.

Audio pre-processing methods and apparatus

A method for eliminating echos in modems used for full-duplex data communication is disclosed. The technique improves the cancellation of the echos by synthesizing an estimate of the desired signal and subtracting this estimate from the received waveform to improve the estimate of the residual echo. An adaptive filter is used to match the transmitted bit pattern to make an estimate of the frequency offset in the far echo, so that it can be cancelled more accurately.

Growing community of inventors

Arlington, MA, United States of America

Thomas F Quatieri, Jr