msm6679a-110 Oki Semiconductor, msm6679a-110 Datasheet

no-image

msm6679a-110

Manufacturer Part Number
msm6679a-110
Description
Si/sd Voice Recognizer, Recorder/player, And Speech Synthesizer
Manufacturer
Oki Semiconductor
Datasheet
MSM6679A-110
Voice Recognition Processor

Related parts for msm6679a-110

msm6679a-110 Summary of contents

Page 1

... Voice Recognition Processor MSM6679A-110 ...

Page 2

... Timing Diagrams .............................................................................................................. 15 Functional Description ...................................................................................................................... 17 Voice Recognition ............................................................................................................. 17 SI Recognition ................................................................................................... 17 SD Recognition ................................................................................................. 20 Name Tag Recording ........................................................................................................ 20 Audio Input Interface ....................................................................................................... 21 Audio Output Interface .................................................................................................... 21 Memory Interface .............................................................................................................. 21 External Voice Synthesis Control ................................................................................... 24 Serial Interface ................................................................................................................... 25 MSM6679A-110 Slave-Mode API .................................................................................................... 26 Command Summary ........................................................................................................ 27 Command Descriptions ................................................................................................... 31 Asynchronous Serial Protocol Example ........................................................................ 44 2 ¡ Semiconductor ...

Page 3

... Oki-defined test procedure). For SD recognition, the MSM6679A-110 stores SD vocabulary templates, as defined by the user, in external SRAM. The MSM6679A-110 can create SD vocabularies words each, with each word using approximately 50 bytes. In addition to providing voice recognition capabilities, the MSM6679A-110 integrates a solid- state recorder/player, speech synthesis functions, and a tone generator ...

Page 4

... Recognition and Input Synthesis Engine Vocabulary Memory Figure 1. MSM6679A-110 Block Diagram A/D Interface Serial-Mode MSM665x Interface PWM Output Serial Interface IC Reset and Oscillator Inputs Figure 2. MSM6679A-110 Logic Symbol 2 System Controller Algorithm Memory External Memory Control AD0 ~ AD7 ADC0 ~ ADC9 VREF A8 ~ A15 NAR ...

Page 5

... RES ADC0 1 ADC1 2 ADC2 3 ADC3 4 ADC4 5 ADC5 6 ADC6 7 ADC7 8 ADC8 9 ADC9 10 AGND 11 Figure 3. MSM6679A-110 84-Pin PLCC Pinout MSM6679A-110 Voice Recognition Processor 53 N/C 52 N/C 51 N/C– A15 50 49 A14 48 A13 A12 47 46 A11 45 A10 AD7 40 AD6 39 ...

Page 6

... MSM6679A-110 Voice Recognition Processor MSM6679A-110 Alphabetic Pin List 84-pin/ 84-pin/ Name Name 100-pin 100-pin AD0 34/28 A10 45/41 AD1 35/29 A11 46/42 AD2 36/30 A12 47/43 AD3 37/31 A13 48/44 AD4 38/32 A14 49/45 AD5 39/33 A15 50/46 AD6 40/34 A15FLIP 56/54 AD7 41/35 ADC0 1/89 A8 43/39 ADC1 2/90 A9 44/40 ADC2 3/91 4 84-pin/ 84-pin/ Name Name Name 100-pin 100-pin BUSY ADC3 ...

Page 7

... Semiconductor Figure 4. MSM6679A-110 84-Pin Package Mechanical Drawing MSM6679A-110 Voice Recognition Processor 5 ...

Page 8

... N/C N N/C RXD1 9 TXD1 10 11 N/C GND 12 OSC0 13 14 N/C OSC1 15 ALE 16 ROMRD 17 WRRAM 18 RDRAM 19 N/C– 20 RESOUT NAR N N/C Figure 5. MSM6679A-110 100-Pin TQFP Pinout 6 ¡ Semiconductor 75 N/C 74 N/C 73 N/C 72 N/C 71 N/C 70 N/C 69 N/C 68 RAMPAGE1 67 RAMPAGE0 LOADPGM 66 65 N/C 64 N/C 63 GND BUSY 60 59 N/C N ROMPAGE1 ...

Page 9

... Semiconductor Figure 6. MSM6679A-110 100-Pin Package Mechanical Drawing MSM6679A-110 Voice Recognition Processor 7 ...

Page 10

... Reserved. This pin is reserved for future use and should be left open. Oscillator 1. When the MSM6679A-110 uses a crystal oscillator, this output is the oscillator output pin. The pin is then connected to one side of a crystal and load capacitor. When used with an external clock, this output is left unconnected ...

Page 11

... Flash Bank Control (Extended Segments). This is the control signal for flash memory banking. MSM665x Next Address Request. This pin signals to the MSM6679A-110 that the external speech synthesis engine is ready for another command. Reserved. These pins are reserved for future use and must be left open. ...

Page 12

... Reserved. This pin is reserved for future use and should be left open. Reserved. This pin is reserved for future use and must be left open. Load Program. This signal allows the MSM6679A-110 to write data to program memory. When asserted low, this signal should set the program memory in write mode ...

Page 13

... Reserved. This pin is reserved for future use and must be tied to VDD. MSM6679A-110 Reset. External logic should assert this power-on reset signal LOW when power is applied to the MSM6679A-110. External ROM Address Select. This control signal enables external ROM execution. This signal is usually connected to ROMPAGE1 and a pullup resistor ...

Page 14

... MSM6679A-110 Voice Recognition Processor ELECTRICAL SPECIFICATIONS Absolute Maximum Ratings Parameter Digital power supply voltage Input voltage Output voltage Analog power voltage Analog reference voltage Analog input voltage Power dissipation Storage temperature 1. Permanent device damage may occur if ABSOLUTE MAXIMUM RATINGS are exceeded. ...

Page 15

... C I Output capacitance C O Analog reference power I REF supply voltage Power consumption Typical condition 25˚C. MSM6679A-110 Voice Recognition Processor Condition Min Applied to AD0-AD7 2.2 Applied to OSC0 0.85 V Applied to all other I/O 0.80 V Applied to AD0-AD7 –0.3 Applied to OSC0 –0.3 Applied to all other I/O –0.3 ...

Page 16

... MSM6679A-110 Voice Recognition Processor AC Characteristics External Program Memory Control (VDD = 4 -40 to 85˚C) Parameter Clock pulse width (OSC) ALE pulse width ROMRD pulse width ROMRD pulse delay time Low address set-up time Low address hold time High address delay time ...

Page 17

... Semiconductor Timing Diagrams CLK ALE ROMRD AD0 - AD7 A8 - A15 CLK ALE RDRAM AD0 - AD7 A8 - A15 MSM6679A-110 Voice Recognition Processor PAD AAS AAH PC0 - 7 t AAD PC8 - 15 Figure 7. ROM Read Timing RAD ...

Page 18

... MSM6679A-110 Voice Recognition Processor CLK ALE WRRAM AD0 - AD7 A8 - A15 WAD AAS AAH RAP0 - 7 t AAD RAP8 - 15 Figure 9. RAM Write Timing ¡ Semiconductor t DH DOUT0 - 7 t AWH ...

Page 19

... Via a special command, the MSM6679A-110 can also return the scores of the input against all defined vocabulary phrases for recognition. This feature allows external host software to select the next best match, if the closest match is not contextually logical ...

Page 20

... MSM6679A-110 Voice Recognition Processor MSM6679A-110 Control Vocabulary Sub-Vocabulary 1 Sub-Vocabulary 2 Phrase Index Phrase Index A/C 1 Low Fan 2 Medium Temperature 3 High Timer 4 Increase Service 5 Decresse Help 6 Set Select 7 Reset — — Cancel — — Clear — — Recall — — On — — Help MSM6679A-110 Direction Vocabulary ...

Page 21

... For example, if the collection is for use in an automobile, conditions such as vehicle speed, road conditions, various window opening positions, heater or AC blower speeds and radio volumes should be varied during the collection. The signal-to-noise ratio should be maintained at 20dB. MSM6679A-110 Voice Recognition Processor Phrase Index Phrase ...

Page 22

... Name tags are used to confirm correct responses in SD recognition. For example phone dialer application, the user associates a “name” (which is recorded into memory) with a phone number. The MSM6679A-110 then plays back the name tag so that the user can verify that the recognized phrase is the correct one. ...

Page 23

... A critical item for high-accuracy speech recognition is correct design of the audio input circuit. A circuit with appropriate gain and frequency responses must be placed between the microphone and MSM6679A-110’s A/D input. Oki recommends input gain and a band pass filter with the following characteristics: • Four pole Chebyshev high-pass filter point at 225 Hz • ...

Page 24

... Per download. Vocabulary swapping by host permits unlimited vocabulary size. The MSM6679A-110 supports Kbytes of RAM per bank, and Kbytes of ROM per bank in separate memory spaces. The 8-bit data bus is multiplexed with the lower eight address bits; the upper eight address bits are not multiplexed. ...

Page 25

... PHH FFFF 0FFFF 10000 13FFF 14000 17FFF 18000 18FFF 1C000 1FFFF Figure 11. MSM6679A-110 Program/Data Memory Map (LOADPGM = “1”) Figure 12 shows the details of the external memory allocation of the MSM6679A-110. MSM6679A-110 Voice Recognition Processor Data Memory 00000 07FFF 08000 0FFFF ...

Page 26

... Figure 12. MSM6679A-110 External Memory Map External Voice Synthesis Control The MSM6679A-110 is capable of interfacing to the MSM665x family of Oki ROM, OTP, or external EPROM speech synthesizers, allowing for up to 260 seconds of high-quality voice and sound effects. The following table indicates the speech capabilities of the MSM665x family. ...

Page 27

... BUSY - Asserted LOW during MSM665x device playback. The MSM6679A-110 F50Bh and F10100xxh commands select this signal for MSM665x command polling. • NAR - Next Address Request status signal. By default, the MSM6679A-110 uses this signal to poll commands to the MSM665x. The F51Bh, F480h, and F440h commands select NAR for polling. • ...

Page 28

... Messages are of variable length. All messages consist of an even number of bytes. Opcodes consist of exactly four bytes, with values between F000h and FEFEh. Operand bytes may take values from 0000h to FFFFh. The MSM6679A-110 issues a return code for many of the host commands. The return code generally consists of the same opcode, followed by data indicating success of failure of the operation ...

Page 29

... Request F520 Select buffer RAM bank for SI/SP. F522 Copy download RAM bank to buffer RAM bank F513 Save download RAM bank templates in first FLASH. (8000 - F2FF) MSM6679A-110 Voice Recognition Processor Description Default (Hex) — 8000 4A00 F100 0005 F123 0101, 0202 ...

Page 30

... Get download RAM bank templates from last FLASH (8000 - FFFF) F502.... Download/upload. F503 xxxx Select/jump. Request F504 Retrieve MSM6679A-110 firmware revision. F505 Initialize background (BG) noise level. F506 Retrieve vocabulary and trigger table revision number. F507 Save SD templates from download RAM to first FLASH. F517 Save SDR templates in last FLASH ...

Page 31

... Rejection: bad signal/noise ratio. Rejection: reason uncertain. Aborting SD Listen mode. After SD utterance search: not found. Rejection. Sort completed. After SD utterance search: empty. Rejection: MSM6679A-110 SD memory full/empty. After SD utterance search: in use. Utt = Utterance ID triggered. Utterance ID, high/low byte of distance. Utterance ID, high/low byte of distance to utterance 1... ...

Page 32

... If in response to an N-byte download request, the MSM6679A-110 then receives N bytes ( even odd) of data from the host odd and N+1 bytes are received, only N bytes are written to MSM6679A-110 memory response to an upload, the MSM6679A-110 then sends N bytes ( even odd) of data to the host. 5. ...

Page 33

... XXYYh = high (XXh) and low (YYh) bytes of requested F102h XXYYh address. The MSM6679A-110 uses and returns an even address outside the MSM6679A-110 work space that is as near as possible to the requested address. Leave this parameter at its default value unless you are using an Oki custom SI vocabulary and are instructed to alter SP/SI recognition origin ...

Page 34

... MSM6679A-110 Voice Recognition Processor Set Parameter (Continued) Operand Set IRQ Level. This command requests direction of host interrupts to IRQ Y. The MSM6679A-110 then selects IRQ Z, where Z is the nearest legal value to Y. Legal IRQ values are F11Yh any from the set {5 (default),A,B,C}. Set SD Recognition SP table. This command sets the SP parameter table number to be used in processing speech input during SD Recognition ...

Page 35

... Power-On/ Values Reset Value After power-on, the MSM6679A-110's mode corresponds to that after issuing a F20C command. This mode may NOT be the optimum condition for most situations, so the user is advised to carefully understand the desired condition and develop a suitable command for the application at hand. ...

Page 36

... These beeps do not cause a F400h message to be issued to the host MCU. When set to 1, the MSM6679A-110 beep can help a user avoid speaking before the MSM6679A-110 is ready. This mode is normally used with a digits vocabulary to pace the user and confirm each utterance reception ...

Page 37

... Semiconductor Recognize Opcode Action Stop Listening. This command causes the MSM6679A-110 to exit Listen mode, F300h whichever was active. Start SI Listen Mode. For all the following opcodes, the MSM6679A-110 performs SI recognition on incoming utterances, using SI vocabulary Y. The vocabulary Y is identified by one of 15 sets, thus Fh. ...

Page 38

... MSM6679A-110 to play back a name tag from external memory F401h ~ sound is defined for a selected index, the F43Dh MSM6679A-110 plays a beep. See the Record commands for information on creating name tags. Speak Phrase from Low Internal Memory sound is defined for a selected index, the MSM6679A-110 plays a beep ...

Page 39

... Speak (Continued) Opcode Action Speak Phrase from High Internal/External Memory sound is defined for a selected index, the MSM6679A-110 plays a beep. The default phrases supplied with the MSM6679A- 110 in the larger upper playback memory area are listed below. F451h "0" simulated DTMF tone. ...

Page 40

... FEFEh Set maximum output level. Request Opcode Action Status Request. This command causes the MSM6679A-110 to return a 2-byte value F500h indicating its current status. F501h Select last FLASH bank for SI recognition. Select download RAM bank for SI/SP template area. This command enables the download ...

Page 41

... Immediately after receiving parameter NL, the MSM6679A-110 responds with a message to indicate acceptance or denial of the transfer request. Acceptance is indicated by F5A0h. Denial is indicated by a F8XYh. At the end of an accepted transfer, the MSM6679A-110 responds with a message to confirm or deny valid completion of the transfer. Valid completion is indicated by F5C0h. F880h Invalid message received ...

Page 42

... Jump to internal program segment. Seg(6~1) Reserved. If Seg(7) =1, not used. Ctl(7)=1 If Seg( and Seg( external program Seg(0) segment 0. If Seg( and Seg( external program segment 1. Retrieve MSM6679A-110 Firmware Revision F504h Number. 40 ¡ Semiconductor Return Value F5E0h Success. F8XYh Failure, with XY( F5E0h Success. F8XYh Failure, with XY( ...

Page 43

... Request (Continued) Opcode Action Initialize in Background. Background noise initialization is performed for 500 ms. The MSM6679A-110 requires this command prior to recognition for noise vector subtraction during the utterance sampling period. Use the background initialization command whenever there is a change in the background noise level. ...

Page 44

... MSM6679A-110 Voice Recognition Processor Record Opcode Action Set Name Tag Length, Set MSM665x Busy Mode ON. Name tag record length is set by XXh, with XXh defining record length in 14-ms F101h intervals. 00XXh The maximum record length of FFh yields a recording interval of 3.57 sec. The default value is 1.2 sec. ...

Page 45

... Erase utterance from SD vocabulary. This command erases the reference parameters for FC00h utterance number XYh from the SD vocabulary, where XYh is the utterance number retained from the previous Search command (F9XYh). MSM6679A-110 Voice Recognition Processor Return Value — — Return Value F501h SDR table is cleared No return value ...

Page 46

... MSM6679A-110 Voice Recognition Processor Asynchronous Serial Protocol Example All messages to the MSM6679A (except downloads and uploads) are echoed, but replies from the MSM6679A to the host are not echoed by the host. This arrangement facilitates manual communication with the MSM6679A using standard terminals. The following table illustrates the range of MSM6679A functions ...

Page 47

... Host initializes MSM6679A. MSM6679A acknowledges. SI recognition. Host starts SI recognition, vocabulary 1. MSM6679A recognizes utterance 3. Host starts SI recognition, vocabulary 2. MSM6679A recognizes utterance 2. Host starts SI recognition, vocabulary 2. MSM6679A recognizes utterance 3. MSM6679A-110 Voice Recognition Processor Action Voice Input "Dial" "Two" "Three" Host MSM6679A Command Response ...

Page 48

... MSM6679A-110 Voice Recognition Processor Comment SD enrollment. Host starts SI recognition, vocabulary 1. MSM6679A recognizes utterance 7. Get ready to train SD utterance 1. Memory is empty and ready to train. Pass 1; host sends SD enroll command. SD utterance 1 initialized. Pass 2; host sends SD enroll command. SD utterance 1 updated. Pass 3. Host sends SD enroll command. ...

Page 49

... Such applications include, but are not limited to: traffic control, automotive, safety, aerospace, nuclear power control, and medical, including life support and maintenance. MSM6679A-110 Voice Recognition Processor Action Voice Input "Jane Doe" ...

Page 50

... MSM6679A-110 Voice Recognition Processor Certain parts in this document may need governmental approval before they can be exported to certain countries. The purchaser assumes the responsibility of determining the legality of export of these parts and will take appropriate and necessary steps, at their own expense, for export to another country ...

Related keywords