Nokia Corporation

Core Wireless Licensing S.a.r.l.

Nokia Technologies Oy

Nokia Mobile Phones Limited

Conversant Wireless Licensing S.a R.l.

Jani Kristian Nurminen

Victor Popa

Jilei Tian

Sakari Himanen

Elina Elisabet Helander

Chenguang Cai

Xia Wang

Ari Heikkinen

Liangfeng Xu

Mikko Tapio Tammi

Koray Ozcan

Anssi Sakari Rämö

Min Chen

Antti Salo

Paavo Ilmari Alku

Antti O Salo

Tuomo Johannes Raitio

Antti Santeri Suni

Martti Tapani Vainio

Jian Tilei

Jilie Tian

Limei Xu

Xuesheng Li

Yi Wang

Hanna Margareeta Silen

Anssi RÄMÖ

An apparatus for providing improved data compression may include an encoder comprising a quantizer for encoding input data and a side model. The quantizer may be trained with respect to high priority data among the input data and may be configured to partially encode the input data by encoding the high priority data. The side model may be trained jointly with the training of the quantizer and is configured to model low priority data among the input data.

Method, apparatus and computer program product for providing improved data compression

A sound producing apparatus with multi-directivity has two or more speakers to produce music or other types of audio sounds. Each of the speakers can produce audio sounds in a certain direction and at least one speaker is steerable so that its sound propagation direction relative to the others can be changed. Furthermore, one or more speakers can produce audio sounds in an adjustable angular range. One or more of the speakers can be dual-mode speakers, each of which can be operated as a wide-angle speaker or a narrow-angle speaker. With multi-directivity, it is possible to play one type of music in one direction and another type of music in another direction to suit the interests of the audience. The apparatus can be a mobile phone, an audio player, a digital or analog recorder/player, or the like.

Multi-directivity sound device

Methods and apparatuses are provided for facilitating speech synthesis. A method may include generating a plurality of input models representing an input by using a statistical model synthesizer to statistically model the input. The method may further include determining a speech unit sequence representing at least a portion of the input by using the input models to influence selection of one or more pre-recorded speech units having parameter representations. The method may additionally include identifying one or more bad units in the unit sequence. The method may also include replacing the identified one or more bad units with one or more parameters generated by the statistical model synthesizer. Corresponding apparatuses are also provided.

Methods and apparatuses for facilitating speech synthesis

An apparatus for providing text independent voice conversion may include a first voice conversion model and a second voice conversion model. The first voice conversion model may be trained with respect to conversion of training source speech to synthetic speech corresponding to the training source speech. The second voice conversion model may be trained with respect to conversion to training target speech from synthetic speech corresponding to the training target speech. An output of the first voice conversion model may be communicated to the second voice conversion model to process source speech input into the first voice conversion model into target speech corresponding to the source speech as the output of the second voice conversion model.

Method, apparatus and computer program product for providing text independent voice conversion

For an enhanced sequential compression of data vectors in a respective compression pass, a current data vector is mapped to at least one current code vector of at least one codebook in at least one quantization stage. The at least one codebook is reordered taking account of at least one intermediate result from the current compression pass and at least one intermediate result from a preceding compression pass. At least one codebook index that is associated in the at least one reordered codebook to the at least one current code vector is then provided for further use. For a decompression of compressed data vectors represented by such codebook indices, at least one codebook index is mapped to at least one code vector of at least one equally reordered codebook.

Compression and decompression of data vectors

A system and method for modeling speech in such a way that both voiced and unvoiced contributions can co-exist at certain frequencies. In various embodiments, three spectral bands (or bands of up to three different types) are used. In one embodiment, the lowest band or group of bands is completely voiced, the middle band or group of bands contains both voiced and unvoiced contributions, and the highest band or group of bands is completely unvoiced. The embodiments of the present invention may be used for speech coding and other speech processing applications.

System and method for modeling speech spectra

An apparatus for providing improved speech synthesis may include a processor and a memory storing executable instructions. In response to execution of the instructions by the processor, the apparatus may perform at least selecting a real glottal pulse from among one or more stored real glottal pulses based at least in part on a property associated with the real glottal pulse, utilizing the real glottal pulse selected as a basis for generation of an excitation signal, and modifying the excitation signal based on spectral parameters generated by a model to provide synthetic speech.

Method, apparatus and computer program product for providing real glottal pulses in HMM-based text-to-speech synthesis

A method and device for improving coding efficiency in audio coding. From the pitch values of a pitch contour of an audio signal, a plurality of simplified pitch contour segments are generated to approximate the pitch contour, based on one or more pre-selected criteria. The contour segments can be linear or non-linear with each contour segment represented by a first end point and a second end point. If the contour segments are linear, then only the information regarding the end points, instead of the pitch values, are provided to a decoder for reconstructing the audio signal. The contour segment can have a fixed maximum length or a variable length, but the deviation between a contour segment and the pitch values in that segment is limited by a maximum value.

Method and system for pitch contour quantization in audio coding

A hybrid approach is described for combining frequency warping and Gaussian Mixture Modeling (GMM) to achieve better speaker identity and speech quality. To train the voice conversion GMM model, line spectral frequency and other features are extracted from a set of source sounds to generate a source feature vector and from a set of target sounds to generate a target feature vector. The GMM model is estimated based on the aligned source feature vector and the target feature vector. A mixture specific warping function is generated each set of mixture mean pairs of the GMM model, and a warping function is generated based on a weighting of each of the mixture specific warping functions. The warping function can be used to convert sounds received from a source speaker to approximate speech of a target speaker.

Hybrid approach in voice conversion

An apparatus for providing improved voice conversion includes a sub-feature generator and a transformation element. The sub-feature generator may be configured to define sub-feature units with respect to a feature of source speech. The transformation element may be configured to perform voice conversion of the source speech to target speech based on the conversion of the sub-feature units to corresponding target speech sub-feature units using a conversion model trained with respect to converting training source speech sub-feature units to training target speech sub-feature units.

Method, apparatus and computer program product for providing improved voice conversion

An apparatus uses a transducer to produce vibration in the ultrasonic frequency range and in the audible frequency range. A membrane or cantilever structure is coupled to the transducer to produce acoustic waves. When the vibration is in the audible frequency range, the membrane structure works like a conventional loudspeaker. When the vibration is in the ultrasonic frequency range, the ultrasonic signal is modulated by audio signal for creating better directivity. The acoustic waves in the ultrasonic frequency range can reproduce directional audible sound due to the nonlinear interaction of ultrasonic waves in air.

Dual-mode loudspeaker

A method and system are introduced that provide dynamic quantizer structures which are configurable during run time. A quantizer configuration and data are stored in a binary format. The dynamic quantizer data is represented as a bitstream, and the bitstream in turn is used as additional input during initialization (or re-initialization/re-configuration) of a speech coder. A configuration header fully specifies the structure and configuration of the dynamic quantizer for each quantized parameter, and the dynamic quantizer data and configurations are fully and dynamically allocated into the speech coder memory. This enables easy re-configuration of a codec associated with the quantizer structures for different scenarios. The use of dynamic quantizer structures in turn enhances compression efficiency of an input signal. The dynamic quantizer structures can also be applied to other compression applications that allow lossy compression.

Dynamic quantizer structures for efficient compression

A contour for a syllable (or other speech segment) in a voice undergoing conversion is transformed. The transform of that contour is then used to identify one or more source syllable transforms in a codebook. Information regarding the context and/or linguistic features of the contour being converted can also be compared to similar information in the codebook when identifying an appropriate source transform. Once a codebook source transform is selected, an inverse transformation is performed on a corresponding codebook target transform to yield an output contour. The corresponding codebook target transform represents a target voice version of the same syllable represented by the selected codebook source transform. The output contour may be further processed to improve conversion quality.

Growing community of inventors

Lempäälä, Finland

Jani Kristian Nurminen