Singlecast interactive radio system

• US 6,246,672 B1
• Filed: 04/28/1998
• Issued: 06/12/2001
• Est. Priority Date: 04/28/1998
• Status: Expired due to Term

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Lumelsky, Leon
• Primary Examiner(s): Ton, Dang
• Assistant Examiner(s): VANDERPUYE, KENNETH N
• Application Number:
  US09/067,878
• Time in Patent Office: 1,141 Days
• Field of Search: 704/500, 704/260, 704/270, 704/272, 704/275, 709/203, 709/201, 709/219, 370/310, 455/550
• US Class Current: 370/310
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: H04L 51/58 Message adaptation for wireless communication
• CPC Class Codes: H04L 67/04 specially adapted for terminals or networks with limited capabilities; specially adapted for terminal portability
• CPC Class Codes: H04L 69/329 in the application layer [OSI layer 7]
• CPC Class Codes: H04L 9/40 Network security protocols

Abstract

A singlecast interactive radio system of the invention delivers digitized audio-based content to subscribers, upon their request, economically and with human voice quality. The system includes personal radio station servers, and a plurality of user terminals, and exploits one of the existing wireless communication networks as a transmission medium. A highly compressed voice-based information content is stored on data network servers, such as Internet World Wide Web servers. The personal radio station server stores multiple subscriber'"'"'s profiles with topics of individual interest, assembles a content material from various Web sites according to the topics, and transmits the content to a subscriber'"'"'s user terminal on subscriber'"'"'s request over the wireless digital network. The user terminal restores voice-based material with at least AM-radio voice quality and transmission costs of such a material is very low in comparison to existing methods of voice communication, at least as a result of chosen compression algorithms. The user terminal optionally integrates, electrically and mechanically, a conventional radio and with a cellular phone equipment. The user can control system functions hands-free by issuing voice commands only. Such functions include, but are not limited to, cellular telephony voice dialing and control, secure network log-on based on voice identification, hands-free tuning to conventional radio-stations, changing audio playback level, and switching between functions. The user terminal also retrieves text material from the Internet or other data depositories, plays the material back as a computer-generated speech, digitizes a voice response from the user, and delivers the response to other e-mail addresses over related networks, including wired networks.

Claims

1. A singlecast interactive radio system, comprising:

an authoring system for generating a phonetically encoded audio information signal in response to data received from an information content provider;

a data repository, operatively coupled to the authoring system, for storing the phonetically encoded audio information signal;

a personal radio system server, operatively coupled to the data repository via a wired communications network, for retrieving at least a portion of the phonetically encoded audio information signal from the data repository upon a request by a system user; and

at least one user terminal, operatively coupled to the server via a wireless communications network, the user terminal being adapted to generate and transmit the request made by the user to deliver the at least a portion of the phonetically encoded audio information signal thereto and to receive and decode the at least a portion of the encoded audio information signal to synthesize an audio signal representative of at least a portion of the data received from the information content provider for playback to the user, the user terminal further including a plurality of prerecorded phonetic unit dictionaries selectively used to provide the audio signal with one of a plurality of narrative voices during playback to the user.

2. The system of claim 1, wherein the phonetically encoded audio information signal includes phonetic and prosodic data.

3. The system of claim 1, wherein the wireless communications network includes at least one advanced mobile phone service (AMPS) channel.

4. The system of claim 1, wherein the wireless communications network includes at least one cellular digital packet data (CDPD) channel.

5. The system of claim 1, wherein the user terminal is adapted to be mobile.

6. The system of claim 1, wherein the user terminal is adapted to be stationary.

7. The system of claim 1, wherein the user terminal further comprises a broadcast band radio tuner for processing broadcast radio signals.

8. The system of claim 1, wherein the user terminal further comprises a wireless telephony interface for receiving and transmitting telephony-related signals.

9. The system of claim 8, wherein the telephony-related signals includes one of voice signals and data signals.

10. An information signal delivery system, comprising:

information signal generating means for generating a phonetically encoded audio information signal in response to data received from an information content provider;

storage means, operatively coupled to the information signal generating means, for storing the phonetically encoded audio information signal;

information signal retrieval means, operatively coupled to the storage means via a wired communications network, for retrieving at least a portion of the phonetically encoded audio information signal from the storage means upon a request by a system user; and

information request and delivery means, operatively coupled to the information signal retrieval means via a wireless communications network, the information request and delivery means including means for generating and transmitting the request made by the user to deliver the at least a portion of the phonetically encoded audio information signal thereto and means for receiving and decoding the at least a portion of the encoded audio information signal to generate an audio signal representative of at least a portion of the data received from the information content provider for playback to the user, the information request and delivery means including means for selecting one of a plurality of narrative voices to be associated with the audio signal heard by the user.

11. The system of claim 10, wherein the information signal retrieval means and the storage means are respective network servers adapted for communication on the wired communications network.

12. The system of claim 10, wherein the wireless communications network includes at least one advanced mobile phone service (AMPS) channel.

13. The system of claim 10, wherein the wireless communications network includes at least one cellular digital packet data (CDPD) channel.

14. The system of claim 10, wherein the information request and delivery means includes a mobile user terminal.

15. The system of claim 10, wherein the information request and delivery means includes a fixed user terminal.

16. The system of claim 10, wherein the information request and delivery means further comprises means for receiving and demodulating a regularly broadcast radio station signal.

17. The system of claim 10, wherein the information request and delivery means further comprises means for receiving and transmitting a telephony-related signal.

18. The system of claim 17, wherein the telephony-related signal includes one of a voice signal and a data signal.

19. In a wireless information signal delivery system including at least one information signal content provider and at least one user terminal, the user terminal comprising:

a control processor;

a wireless modem, operatively coupled to the control processor, for demodulating a received phonetically encoded information signal representative of audio-based data provided by the at least one information signal content provider and for modulating a user-initiated signal;

a speech recognizer, operatively coupled to the control processor, having a speech input portion for receiving a spoken utterance provided by a user, the spoken utterance representing at least a request for certain audio-based data provided by the at least one information signal content provider, the speech recognizer decoding the spoken utterance and presenting the decoded utterance to the control processor, the control processor generating a user-initiated signal in response thereto;

a speech synthesis system for generating a synthesized speech signal in response to the demodulated phonetically encoded information signal, the speech synthesis system including a plurality of prerecorded phonetic unit dictionaries selectively used to provide the synthesized speech signal with one of a plurality of narrative voices during playback to the user;

audio playback means, operatively coupled to the speech synthesis system, for generating an audio signal in response to the synthesized speech signal for playback to user.

20. The user terminal of claim 19, further comprising a wireless telephony interface for processing telephony-related communications received by the wireless modem for output by the playback means and for generating telephony-related communications provided by the user for transmission by the wireless modem.

21. The user terminal of claim 19, further comprising a broadcast radio signal tuner, operatively coupled to the control processor and the audio playback means, for processing a regularly broadcast radio signal for output by the audio playback means.

22. The user terminal of claim 21, wherein the regularly broadcast radio signal tuner includes one of an AM and FM tuner.

23. The user terminal of claim 19, further comprising background audio mixing means, operatively coupled to the audio playback means, for processing a background audio signal, included with the phonetically encoded information signal, for playback to the user with the audio signal generated from the synthesized speech signal.

24. The user terminal of claim 23, wherein the background audio signal is in a musical instrument digital interface (MIDI) format.

25. The user terminal of claim 19, wherein the speech synthesis system further comprises:

a phonemes-to-allophones converter for converting phonemes associated with the demodulated phonetically encoded information signal to allophones;

wherein the plurality of prerecorded phonetic unit dictionaries are operatively coupled to the phonemes-to-allophones converter via user-responsive switching means, and store previously recorded allophones respectively associated with the narrative voices and wherein the previously recorded allophones which substantially match the allophones provided by the allophone converter are selected; and

a speech codec, operatively coupled to the plurality of prerecorded phonetic unit dictionaries, for generating the synthesized speech signal representative of the information signal in response to the previously recorded allophones from the selected dictionary.

26. The user terminal claim 19, wherein the spoken utterance represents audio playback commands and further wherein the speech recognizer decodes the spoken utterance and presents the decoded utterance to the control processor, the control processor generating a control signal in response thereto and providing the control signal to the audio playback means to control the audio playback.

27. In a wireless information signal delivery system including at least one information signal content provider and at least one user terminal, the user terminal comprising:

control processing means;

memory means operatively coupled to the processing means;

wireless modem means, operatively coupled to the memory means, for demodulating a received phonetically encoded information signal representative of audio-based data provided by the at least one information signal content provider and for modulating a user-initiated signal;

speech recognition means, operatively coupled to the control processing means, having speech input means for receiving a spoken utterance provided by a user, the spoken utterance representing at least a request for certain audio-based data provided by the at least one information signal content provider, the speech recognition means decoding the spoken utterance and presenting the decoded utterance to the control processing means, the control processing means generating a user-initiated signal in response thereto;

speech synthesis means, operatively coupled to the memory means, for generating a synthesized speech signal in response to the demodulated phonetically encoded information signal, the speech synthesis means including a plurality of prerecorded phonetic unit dictionaries selectively used to provide the synthesized speed signal with one of a plurality of narrative voices during playback to the user; and

audio playback means, operatively coupled to the speech synthesis means, for generating an audio signal in response to the synthesized speech signal for playback to a user.

28. The user terminal of claim 27, further comprising wireless telephony means, operatively coupled to the speech input means, the wireless modem means and the audio playback means, for processing telephony-related communications received by the wireless modem means for output by the playback means and for generating telephony-related communications provided by the user at the speech input means for transmission by the wireless modem means.

29. The user terminal of claim 27, further comprising regularly broadcast radio signal processing means, operatively coupled to the control processing means and the audio playback means, for processing a regularly broadcast radio signal for output by the audio playback means.

30. The user terminal of claim 29, wherein the regularly broadcast radio signal processing means includes one of an AM and FM tuner.

31. The user terminal of claim 27, further comprising background audio mixing means, operatively coupled to the memory means and the audio playback means, for processing a background audio signal, included with the phonetically encoded information signal, for playback to the user with the audio signal generated from the synthesized speech signal.

32. The user terminal of claim 31, wherein the background audio signal is in a musical instrument digital interface (MIDI) format.

33. The user terminal of claim 27, wherein the speech synthesis means further comprises:

a phonemes-to-allophones converter, operatively coupled to the memory means, for converting phonemes associated with the demodulated phonetically encoded information signal to allophones;

wherein the plurality of prerecorded phonetic unit dictionaries are operatively coupled to the phonemes-to-allophones converter via user-responsive switching means, and store previously recorded allophones respectively associated with the narrative voices and wherein the previously recorded allophones which substantially match the allophones provided by the allophone converter are selected; and

speech decoding, operatively coupled to the dictionaries, for generating the synthesized speech signal representative of the information signal in response to the previously recorded allophones from the selected dictionary.

34. The user terminal claim 27, wherein the spoken utterance represents audio playback commands and further wherein the speech recognition means decodes the spoken utterance and presents the decoded utterance to the control processing means, the control processing means generating a control signal in response thereto and providing the control signal to the audio playback means to control the audio playback.

35. A client/server system comprising:

at least one client terminal adapted to generate a user-initiated signal upon a user request, to receive and decode data, and to synthesize an audio signal representative of at least a portion of the data for playback to the user in one of a plurality of narrative voices selected by the user, the portion of the data comprising a phonetically encoded audio information signal;

an information retrieval and delivery server, operatively coupled to a wide area network having data servers containing a variety of types of data, and operatively coupled to the at least one client terminal via a wireless communications network, the information retrieval and delivery server including;

memory means; and

processing means, operatively coupled to the memory means, including;

means for receiving user-related information from the at least one client terminal and storing the user-related information in the memory means;

means for retrieving data from at least one data server on the wide area network and storing the data in the memory means in response to the user-related information receipt and storage means; and

means for transmitting the retrieved data to the at least one client terminal.

36. The system of claim 35, wherein the data retrieval means retrieves data from the network at the request of the user.

37. The system of claim 35, wherein the data retrieval means autonomously retrieves data from the network.

38. The system of claim 35, wherein the processing means further comprises user identification and authorization means, responsive to the user-initiated signal, for identifying the user and authorizing the user prior to the information server retrieving data from the network.

39. The system of claim 35, wherein the processing means further comprises means for comparing data retrieved by the information server for one user to data requested by another user prior to retrieving the newly requested data from the network.